geiger-scan@0.4.0
CAUTION· startup onlyPublisher claims: "A Geiger counter for AI agents: one read-only command that inventories every agent, harness, MCP server, plugin, and AI extension on a machine — and what each can touch." 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
- no credential variables read in the code
- 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
- the tool list (the server exited before answering) · what the tools do when called with real credentials
Connect it under the guard. Startup only; authenticated tool behavior not tested. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 2026-11-18 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Image alt text carrying instructions; Image alt text carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 20 s · 2 scenariosStatic findings
npx geiger-scan --json out.json also write machine-readable findingsFix: Pin versions and sources; vendor anything fetched at install time.A geiger scan: findings grouped by ecosystem with exposure labels, a redacted credential, and plain-language fixesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx geiger-scan --path D:\\repo1 --path E:\\repo2Fix: Pin versions and sources; vendor anything fetched at install time.The HTML report: summary tiles, exposure chips, credential shapes, and "What to do" remediation blocksFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.npx geiger-scan --home C:\\Users\\otherFix: Pin versions and sources; vendor anything fetched at install time.npx geiger-scan scan and print the terminal reportFix: Pin versions and sources; vendor anything fetched at install time.…redential-file-read', note: 'reads a credential file (SSH key, AWS credentials, /etc/shadow)', re: /(\.ssh[\\/]id_(rsa|ed25519|ecdsa|dsa)\b|\.aws[\\/]credentials\b|\/etc\/…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…an outside destination', re: /\bexfiltrat|\b(send|upload|post)\b[^.\n]{0,40}\b(\.env|credential|secret|api[_-]?key|token|private key)\b/i }, { id: 'bypass-approva…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.npx geiger-scan --html report.html also write a self-contained HTML reportFix: Pin versions and sources; vendor anything fetched at install time.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 geiger-scan@0.4.0 as of 48 min ago. This is the package itself, not its dependencies.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.config/Claude/claude_desktop_config.json, ~/.config/Code/User/mcp.json, ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json.
- Unclaimed publisher≈ +8 on the totalClaim atomburstofficial: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- 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.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.