aibtc-news-sales
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external platforms which can be used to influence the agent's behavior via indirect prompt injection.\n
- Ingestion points: The skill reads data from the aibtc.com agent registry, Moltbook posts, and the agent's own inbox (SKILL.md Step 1).\n
- Boundary markers: There are no documented delimiters or instructions to ignore embedded commands within the processed data.\n
- Capability inventory: The agent can execute local scripts via
bun runand has access towalletandsigningcapabilities for blockchain transactions (AGENT.md Decision Logic, SKILL.md frontmatter).\n - Sanitization: No input validation or sanitization routines are mentioned for the content retrieved from external sources.\n- [COMMAND_EXECUTION]: The agent is configured to run local TypeScript scripts using the Bun runtime.\n
- Evidence: The decision logic in AGENT.md triggers
bun run aibtc-news-classifieds/aibtc-news-classifieds.tsfor listing management operations.\n - Context: While the scripts appear to be vendor-provided dependencies, the ability to execute code remains a high-impact capability if the agent is manipulated via its external data inputs.
Audit Metadata