krusch-grounded-harness@0.2.1
CAUTION· startup onlyPublisher claims: "Turn-0 workspace grounding, spin-loop blocker, and defect-only stop gate for AI coding agents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Startup only; authenticated tool behavior not tested.- Tested
- server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
- Not tested
- the tool list (the server exited before answering) · what the tools do when called with real credentials
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
GEMINI_API_KEYConfiguration, not credentials: OLLAMA_HOST, OLLAMA_MODEL, OLLAMA_URL- Where it talks to
- no vendor host named in the code
- What we saw when it ran
- no credential files read · no network
- What we could not test
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it with a scoped credential, under the guard. It asks for GEMINI_API_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; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 39 s · 2 scenarios · 0 deviationsStatic findings
{ tool: 'bash', args: { command: 'rm -rf /' }, alwaysForbidden: true },Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./\b(?:dict\s*\(\s*os\.environ\s*\)|os\.environ\.copy\s*\(\s*\)|JSON\.stringify\s*\(\s*process\.env\b)/;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return name === '.env' || name.startsWith('.env.') || name === '.DS_Store' || SQLITE_SIDECAR_RE.test(name);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.{ tool: 'bash', args: { command: 'cat .env' }, alwaysForbidden: true }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.{ tool: 'bash', args: { command: 'rm -rf /' }, alwaysForbidden: true },Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- `config.json` & `.env.example` — Default port (`3782`), service name, `DB_PATH`, `DATA_DIR`, and `LOG_DIR`.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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 krusch-grounded-harness@0.2.1 as of 44 min ago. This is the package itself, not its dependencies.
What would make this Verified
10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim krusch: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.