open-skills-mcp@0.2.3
CAUTION· not startedPublisher claims: "A universal MCP skill runtime executing in a secure Docker sandbox." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
S3_ACCESS_KEYS3_SECRET_KEYConfiguration, not credentials: HOST_IP, HOST_SKILL_PATH, HOST_WORK_DIR, OPEN_SKILLS_IMAGE, S3_BUCKET, S3_CUSTOM_DOMAIN, S3_ENDPOINT, S3_REGION- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for S3_ACCESS_KEY, S3_SECRET_KEY and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
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 ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
- **Permissions**: You are user `agent` (uid=1000). You have read/write access to `/share`, but NO root/sudo access.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.RUN mkdir -p /ms-playwright && chmod 777 /ms-playwrightFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.- Writing to `/share/output.txt` will immediately create `output.txt` in your IDE project root.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.&& npm install -g npm@latest \Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.<summary><strong>🔧 Development Installation</strong></summary> If you are a developer and want to run or debug from source code: ### Running Modes #### Mode A:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.&& chown -R agent:agent /app /share /home/agentFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for open-skills-mcp@0.2.3 as of 19 h ago. This is the package itself, not its dependencies.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.