Is hermoso safe to use?

hermoso scores 36/100 (grade F) on the Canopii Trust Index, and carries 3 confirmed security failures that cap its score: Tool descriptions free of injection markers, No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. It passes 15 of the 27 controls that apply to it.

What security issues does hermoso have?

hermoso fails 3 controls: Tool descriptions free of injection markers, No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.

How reliable is the security score for hermoso?

We could evaluate 99% of the controls that apply to hermoso. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.

Does hermoso have any security advisories?

hermoso has 8 non-scoring advisories — observations worth a human review that deliberately do not affect the deterministic score, since they can be noisy.

How was hermoso scored?

Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

hermoso MCP Server Security Report

io.github.hermoso-ai/hermoso

718 tools, all usable alone: ad research, video ads, 10 publishing channels, 11 ad platforms.

36F

Security Trust Score

Grade F · Serious issues

Tier 1 · Public sourceHigh confidence · 99%latest v0.1.163 Repository Publisher-verified

Declared MCP capabilities

ResourcesPrompts

Run it securely

This server scored F. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

Are you the maintainer?

Verify with GitHub to get alerted whenever hermoso-ai/hermoso changes score — and claim the badge for your README.

Claim this server

3 issues capping this score

highTool descriptions free of injection markers — 3 marker(s) across 3 tool(s)
highNo risky post-publish tool changes (rug-pull) — 2 risky tool-definition change(s) in version history (0.1.15 → 0.1.25)
mediumNo over-broad / destructive tools — 13 over-broad tool(s)

The short answer

Is hermoso safe to use?: hermoso scores 36/100 (grade F) on the Canopii Trust Index, and carries 3 confirmed security failures that cap its score: Tool descriptions free of injection markers, No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. It passes 15 of the 27 controls that apply to it.
What security issues does hermoso have?: hermoso fails 3 controls: Tool descriptions free of injection markers, No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.
How reliable is the security score for hermoso?: We could evaluate 99% of the controls that apply to hermoso. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
Does hermoso have any security advisories?: hermoso has 8 non-scoring advisories — observations worth a human review that deliberately do not affect the deterministic score, since they can be noisy.
How was hermoso scored?: Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.

Reputation0stars0forks6.8kdownloads/mo1open issues4d agolast commit<1yage

Security controlslatest scored version v0.1.163

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

Fail
Indirect Prompt Injection (IPI) Defensesguard3 marker(s) across 3 tool(s)
Tool/prompt/resource text is free of hidden instructions that could hijack the agent. How many servers fail this?
update_pinterest_board — pre-action injectionmoderate_youtube_comment — conceal-from-user directivemanage_meta_partnership_creator — conceal-from-user directive
Fix: Remove hidden directives, HTML/comment instructions, and override phrasing from descriptions.
Fail
Tool Definition Integrityguard2 risky tool-definition change(s) in version history (0.1.15 → 0.1.25)
Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns. How many servers fail this?
post_to_metamake_template_ad
Fix: Never add hidden directives or destructive scope to an already-published tool; document description changes in release notes.
Fail
User-in-the-Loop / Approval Scopeguard13 over-broad tool(s)
No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval. How many servers fail this?
create_branddelete_brandpost_to_metapost_to_pinterest
Fix: Scope tools narrowly; avoid arbitrary command execution and destructive defaults.
Warn
Strict JSON Schema Enforcementschemas not strict
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
Fix: Set additionalProperties:false and require explicit parameters on every tool.

Application Security Checks

Warn
No path traversalguard5 occurrences
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
bin/hermoso.mjs:50bin/hermoso.mjs:53bin/hermoso.mjs:103mcp/http.mjs:224
Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.
Warn
No SSRF sinksguard10 occurrences
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
bin/hermoso.mjs:177mcp/client.mjs:81mcp/client.mjs:102mcp/client.mjs:107
Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.
Warn
Dependencies pinned (lockfile)no lockfile found
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).
Warn
Published with provenanceno provenance attestation
Build provenance attests the artifact was built from the claimed source by CI.
Fix: Publish with npm provenance (--provenance) from a trusted CI.
Warn
Established maintainersingle maintainer
Brand-new / single anonymous maintainers raise takeover and malware risk.
Fix: Publish under an established account/org; add multiple maintainers.
Warn
Has a security policyno security policy
A SECURITY.md gives a private path to report vulnerabilities.
Fix: Add SECURITY.md with a disclosure contact and process.
Pass
No command-injection sinksguardno sinks found
Untrusted tool input reaching a shell yields remote code execution.
Pass
No dynamic code executionguardno sinks found
eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.
Pass
No unsafe deserializationguardno sinks found
pickle/yaml.load/etc. on untrusted data can execute code.
Pass
No committed secretsguardno secrets found
Hardcoded keys/tokens in published source are live credentials an attacker can use.
Pass
Credentials sourced from environmentreads credentials from environment
Reading secrets from env/secret stores avoids hardcoding them.
Pass
No known-vulnerable dependencies1 runtime deps, no known CVEs
Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.
Pass
No install/post-install scriptsguardno install scripts
install hooks run arbitrary code on every consumer at install time.
Pass
Package name not typosquattingguarddistinct package name
Names mimicking popular packages are a common malware delivery vector.
Pass
Actively maintainedrecent commits
Unmaintained servers don't receive security fixes.
Pass
Repository not archivedguardactive
Archived repositories will never be patched.
Pass
Declares a licenseMIT
A clear license is required for legal enterprise use.
Pass
Adoption & popularityestablished adoption
A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.
Not checked
Signed releasesnot evaluated
Signed releases let consumers verify artifacts weren't tampered with.

Transport & Trust Model

Warn
Execution Sandboxingruns natively (no container image)
A container/sandbox image limits blast radius; a server that runs natively has full host access.
Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.
Pass
Transport Encryption (TLS)guardall remotes use HTTPS
Plaintext HTTP exposes traffic and bearer tokens to interception.
Pass
IAM / Authentication ScopingOAuth / PRM handling detected
OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.
Pass
Network Exposureno bind-all detected
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
N/A
Live Endpoint Reachablenot dynamically scanned
A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.
N/A
Authentication Enforced (live)not dynamically scanned
If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

AI-flagged — for review

Observations from an AI review of tool descriptions. These are advisory only and do not affect the score — they can be noisy and need human judgement.

info
Tool "enable_tools" description changed after publish
Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.
info
Tool "list_inbox" description changed after publish
Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.
info
Tool "reply_to_inbox_item" description changed after publish
Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.

Show 5 more

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

markdown

[![Canopii Trust Score](https://index.canopii.dev/api/badge/io.github.hermoso-ai/hermoso)](https://index.canopii.dev/server/io.github.hermoso-ai/hermoso)

html

<a href="https://index.canopii.dev/server/io.github.hermoso-ai/hermoso"><img src="https://index.canopii.dev/api/badge/io.github.hermoso-ai/hermoso" alt="Canopii Trust Score" /></a>

Versions

Version	Score	Status	Published
v0.1.163latest	36F	scored	8/27/2026
v0.1.142	36F	scored	8/24/2026
v0.1.139	36F	scored	8/20/2026
v0.1.90	13F	scored	8/15/2026
v0.1.86	13F	scored	8/13/2026
v0.1.85	13F	scored	8/12/2026
v0.1.71	13F	scored	8/10/2026
v0.1.43	36F	scored	8/4/2026
v0.1.25	36F	scored	8/1/2026
v0.1.15	40D	scored	7/23/2026
v0.1.8	88B	scored	7/20/2026
v0.1.7	86B	scored	7/19/2026
v0.1.5	87B	scored	7/16/2026

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.