io.github.dcostenco/prism-mcp v20.8.2

16F

Security Trust Score

Grade F · Serious issues

Tier 1 · Public sourceHigh confidence · 98%rubric 2.8.1

Declared MCP capabilities

ResourcesPrompts

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

1 issue capping this score

criticalNo command-injection sinks — 4 occurrences

Reputation155stars24forks0open issues16d 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.
Warn
Tool Definition Integrityguard9 tool description(s) drifted after publish (no risk signals in diff)
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.
brave_web_searchsession_load_contextsession_save_ledgersession_save_handoff
Fix: Never add hidden directives or destructive scope to an already-published tool; document description changes in release notes.
Pass
Indirect Prompt Injection (IPI) Defensesguardno injection markers
Tool/prompt/resource text is free of hidden instructions that could hijack the agent.
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 command-injection sinksguard4 occurrences
Untrusted tool input reaching a shell yields remote code execution. How many servers fail this?
scripts/prism-agent.mjs:441src/scholar/freeSearch.ts:142src/scholar/freeSearch.ts:147src/utils/normalizeToolCallFormat.ts:38
Fix: Never pass tool arguments to a shell; use argv arrays with shell disabled.
Warn
No path traversalguard100 occurrences
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
scripts/__tests__/tools.test.mjs:128scripts/__tests__/tools.test.mjs:133scripts/__tests__/tools.test.mjs:331scripts/__tests__/tools.test.mjs:338
Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.
Warn
No SSRF sinksguard60 occurrences
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
examples/langgraph-agent/tools.py:220scripts/knowledge-ingest/ingest.mjs:32scripts/knowledge-ingest/ingest.mjs:52scripts/migrate-local-to-portal.mjs:48
Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.
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 dependencies231 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
Dependencies pinned (lockfile)lockfile present
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Pass
Actively maintainedrecent commits
Unmaintained servers don't receive security fixes.
Pass
Repository not archivedguardactive
Archived repositories will never be patched.
Pass
Declares a licenseApache-2.0
A clear license is required for legal enterprise use.
Pass
Has a security policySECURITY.md present
A SECURITY.md gives a private path to report vulnerabilities.
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.
N/A
No install/post-install scriptsguardno published package
install hooks run arbitrary code on every consumer at install time.
N/A
Package name not typosquattingguardno published package
Names mimicking popular packages are a common malware delivery vector.
N/A
Published with provenanceno published package
Build provenance attests the artifact was built from the claimed source by CI.
N/A
Established maintainerno published package
Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

Warn
Network Exposurebinds 0.0.0.0
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
Fix: Bind to 127.0.0.1 by default; never ship open debug endpoints.
Pass
Execution Sandboxingcontainerized
A container/sandbox image limits blast radius; a server that runs natively has full host access.
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 (80)

GodotUnityXcodelevelDefoldFlutterprojectGameMakerfetch_urlread_fileshell_runskill_saveConstruct 3prism_inferaba_protocolskill_manageUnreal EngineVisual Studioapi_analyticsbrave_answersAndroid Studioagent_registerlist_directorymemory_historyresume_sessionagent_heartbeatagent_list_teambackup_databasememory_checkoutverify_behaviorbrave_web_searchextract_entitiesknowledge_forgetknowledge_ingestknowledge_searchknowledge_upvotenpm_package_infoprism-mcp-serverscholar_researchPrism Mind Palaceinference_metricsonboarding_wizardpypi_package_infosession_bootstrapbrave_local_searchdeep_storage_purgeknowledge_downvotemaintenance_vacuumsession_save_imagesession_task_routesession_view_imageGPU Compute Clustercode_mode_transformsession_save_ledgerGame Dev Workstationknowledge_sync_rulesquery_memory_naturalsession_detect_driftsession_health_checksession_load_contextsession_save_handoffSession Handoff Statesession_export_memorysession_forget_memorysession_search_memorysession_abort_pipelinesession_backfill_linkssession_compact_ledgersession_start_pipelineconfigure_notificationsknowledge_set_retentionsession_cognitive_routesession_save_experiencesession_intuitive_recallsession_synthesize_edgesbrave_web_search_code_modesession_backfill_embeddingsbrave_local_search_code_modesession_check_pipeline_statusgemini_research_paper_analysis

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 "brave_web_search" 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 "session_load_context" 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 "session_save_ledger" 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