jt-read-board
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process the contents of
card-loop/board.md, which is a data ingestion surface that could contain malicious instructions. - Ingestion points: The agent is instructed to read
card-loop/board.mdand report its contents based on specific keywords. - Boundary markers: There are no explicit boundary markers or instructions to treat the file content as untrusted data.
- Capability inventory: The skill possesses file-reading and natural language reporting capabilities.
- Sanitization: No sanitization, filtering, or validation of the markdown file's content is implemented before the agent processes and reports it.
Audit Metadata