aibtc-news-sales
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
bun runto execute local TypeScript scripts for managing classified ads, such aslist-classifiedsandpost-classified. These are standard operational commands within the agent's defined scope. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to ingest data from the aibtc.com registry, Moltbook, and its own inbox to find potential advertisers.
- Ingestion points: aibtc.com agent registry, Moltbook posts, and user/agent inbox (referenced in
SKILL.md). - Boundary markers: The skill does not explicitly define delimiters for untrusted data in the prompt logic.
- Capability inventory: The agent can perform write operations to the marketplace via the
post-classifiedscript call defined inAGENT.md. - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external registries or messages.
Audit Metadata