CanopiiCanopiiAll serversEnterprise →
io.github.mohitagw15856/pm-claude-skills

io.github.mohitagw15856/pm-claude-skills v76.1.0

Security Trust Score
Grade C · Needs review
Tier 1 · Public sourceHigh confidence · 98%
Declared MCP capabilities
ResourcesPrompts

Run it through Canopii Gateway — policy enforcement, audit trail, and per-user attribution on every call.

1 issue capping this score
  • mediumNo install/post-install scripts — runs postinstall
Reputation1.3kstars227forks9.0kdownloads/mo11open issues17d agolast commit<1yage

Security controls

Deterministic, evidence-backed. Score earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • 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.

  • Pass
    Indirect Prompt Injection (IPI) Defensesguardno injection markers

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

  • Pass
    Tool Definition Integrityguardtool definitions stable; no risky changes in version history

    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.

  • Pass
    User-in-the-Loop / Approval Scopeguardno destructive tool scope

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

Application Security Checks

  • Fail
    No install/post-install scriptsguardruns postinstall

    install hooks run arbitrary code on every consumer at install time. How many servers fail this?

    Fix: Remove preinstall/install/postinstall scripts, or document and minimize them.

  • Warn
    No path traversalguard3 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    web/artifacts.js:230web/export-doc.js:137web/export-doc.js:137

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    No SSRF sinksguard5 occurrences

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

    web/app.js:108web/live.js:10web/live.js:14web/providers.js:244

    Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.

  • Warn
    Credentials sourced from environmentno env-based config detected

    Reading secrets from env/secret stores avoids hardcoding them.

    Fix: Read credentials from environment variables or a secret manager.

  • 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
    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
    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
    Package name not typosquattingguarddistinct package name

    Names mimicking popular packages are a common malware delivery vector.

  • Pass
    Published with provenancepublished with provenance

    Build provenance attests the artifact was built from the claimed source by CI.

  • 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
    Network Exposureno bind-all detected

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

  • N/A
    Transport Encryption (TLS)guardno remote endpoints

    Plaintext HTTP exposes traffic and bearer tokens to interception.

  • N/A
    IAM / Authentication Scopingno remote endpoints

    OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

  • 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.

Tools (42)

Turn a skillSimulate the acquirerHire an AI agent the way youAudit whether the organisationOffboard an AI agent the way youCheck AI output before you trust or use it — where itAssess whether and how someone can safely stay in their ownConduct a structured ethical review of an AI or ML feature,Figure out which AI tool actually fits the task in front ofOptimize an article for Answer Engine Optimization (AEO) soPlan a trip that actually works with a disability or accessAudit a content library, docs site, or blog for AI-generatedBuild a structured account plan for any key customer or targBuild an all-hands that lands with everyone from intern to VDecide when and how your product and communications must (orDesign a 360-degree feedback survey or write a structured 36Design an evaluation plan for an LLM or AI feature before shDesign statistically rigorous A/B tests for product featuresGenerate a WCAG 2.2 accessibility audit checklist and remediPrepare the conversations with aging parents that everyone pReview AI-authored code for its characteristic failure modesReview an LLM agent design and find where it will be unreliaRun a blameless postmortem for an incident caused by an AI aRun a club, PTA, or association AGM that finishes on time anSpecify an autonomous or tool-using AI agent before buildingSpecify the tracing, metrics, and alerting for an AI agent oStructure AI and ML product decisions with the rigour of anyWrite a PRD for an AI-powered feature, covering the things nWrite platform-native paid ad copy with multiple angles to tDesign an AI-assisted workflow for a recurring task — whichAnalyse a finished A/B test and write the readout — the resuAudit whether AI agents can actually use your product — docsBuild the context an AI needs to do a task well — the backgrCheck live air quality anywhere with zero API keys — Open-MeDecode a 401k or workplace retirement plan — the real cost oEnforce the simplest meeting rule that works — no agenda, noEvaluate performance fairly when output is AI-assisted — whaGet back into a locked or hacked account the right way — theRedesign seat-based pricing for the agent era — when one humRequest a reasonable accommodation at work or in education —Work through the first hours and days after a disaster — a fWrite an AI usage policy people can actually follow — approv