aibtc-news-classifieds
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script uses
Bun.spawnto call a local signing utility (signing/signing.ts) for BIP-322 message signing. This is a controlled execution of a sibling skill intended for secure authentication. - [INDIRECT_PROMPT_INJECTION]: The skill processes and displays external data (classified ad bodies, signal corrections, and daily briefs) fetched from the aibtc.news API, which could potentially contain malicious instructions aimed at the agent.
- Ingestion points: Data is ingested through
apiGet,x402Get, andx402Postfunctions inaibtc-news-classifieds.ts, specifically from the/classifieds,/signals, and/briefendpoints. - Boundary markers: The skill prints raw JSON output to the console without explicit delimiters or instructions to the agent to ignore embedded commands within the fetched data.
- Capability inventory: The skill can perform network operations via
fetchand initiate authenticated write operations (POST/PATCH) by invoking thesigningtool. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the API before it is presented to the agent context.
Audit Metadata