Skills/PyPI/shared-skills-registry-mcp

shared-skills-registry-mcp@0.1.0a2

CAUTION· static only

Publisher claims: "A self-hosted registry and MCP server for reusable AI-agent skills" Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher cobibean · publishing for 129 daysInstalls 51Last detonated 2 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
SSR_MCP_AUTH_TOKENConfiguration, not credentials: SSR_MCP_ALLOW_SKILLS_ROOT_OVERRIDE, SSR_MCP_AUDIT_LOG, SSR_MCP_BIND, SSR_MCP_PORT, SSR_MCP_SHARED_SKILL_CONTENT_ROOTS, SSR_MCP_SHARED_SKILLS, SSR_MCP_SKILLS_ROOT, SSR_MCP_URL, XDG_STATE_HOME
Where it talks to
no vendor host named in the code
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

LOW
Authorization escalation languageREADME.md:157 · Authorization escalation language · informational: not an instruction file…y beneath the adapter-configured `SSR_MCP_SKILLS_ROOT`. Model-supplied per-call root overrides are rejected by default. The repository-relative `client/stdio_server.py` rema…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languagedocs/SECURITY-BOUNDARY.md:21 · Authorization escalation language · informational: not an instruction file…he previous installation when possible. - Missing root configuration, attempted root override, checksum failure, path escape, and frontmatter mismatch fail closed. Local ins…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill command.github/workflows/ci.yml:53 · Process kill command — agent can terminate processesif [[ -n "${server_pid:-}" ]] && kill -0 "$server_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill command.github/workflows/ci.yml:76 · Process kill command — agent can terminate processesif ! kill -0 "$server_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill command.github/workflows/ci.yml:205 · Process kill command — agent can terminate processeskill "$server_pid" || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languagedocs/THREAT-MODEL.md:54 · Authorization escalation language · informational: not an instruction file…eats its configured `SSR_MCP_SKILLS_ROOT` as authoritative and rejects per-call root overrides by default. ### Skill author or upstream source Skill content is untrusted i…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill command.github/workflows/ci.yml:204 · Process kill command — agent can terminate processesif [[ -n "${server_pid:-}" ]] && kill -0 "$server_pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languagedocs/MCP-CLIENT-CONFIG.md:35 · Authorization escalation language · informational: not an instruction file…en a trusted caller must select a per-call local root; otherwise model-supplied root overrides are rejected. | | `PYTHONPATH` | legacy raw-script use only | Set to the repo …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_mcp_stdio_e2e.py:68 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/shared_skills_registry_mcp/cli.py:30 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Print a fresh SSR bearer token as a ready-to-paste .env line."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill command.github/workflows/ci.yml:54 · Process kill command — agent can terminate processeskill "$server_pid" || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈21,179 tok
14 files · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for shared-skills-registry-mcp@0.1.0a2 as of 1 h ago. This is the package itself, not its dependencies.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cobibean: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cobibeanPropose a patch to the maintainer