tek-read-board
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes the content of
card-loop/board.md. If this file contains untrusted content, it could potentially influence the agent's behavior during the reporting phase. However, the risk is mitigated by explicit instructions that forbid the agent from making changes or executing actions beyond reporting. - Ingestion points: The skill reads from
card-loop/board.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the board file.
- Capability inventory: The skill is limited to reading files and generating a report; it explicitly prohibits editing files, performing checkouts, or taking action ('ห้ามแก้ไฟล์ ห้ามลงมือ ห้าม checkout').
- Sanitization: No sanitization or validation of the board file content is performed before processing.
Audit Metadata