aibtc-news-classifieds

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script signing/signing.ts using Bun.spawn to handle BIP-322 message signing. This is a standard project pattern for delegating sensitive cryptographic operations to a specialized component.- [EXTERNAL_DOWNLOADS]: The skill fetches data from https://aibtc.news/api to list classified ads, check streaks, and retrieve editorial guidelines. These requests are necessary for the skill's primary function and target the vendor's official API.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests and processes external content from the aibtc.news API (such as classified ads and briefs). Ingestion points: API response data in aibtc-news-classifieds.ts via apiGet and x402Get. Boundary markers: None present in instructions or script output. Capability inventory: Fund expenditure via x402 (post-classified, get-brief) and data modification via signed API requests (correct-signal, update-beat). Sanitization: None; outputs raw JSON to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 03:10 AM