write-implementation-plan
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and act upon external project specifications, which could contain malicious or conflicting instructions.
- Ingestion points: Reads approved specifications, project instructions, and code (SKILL.md).
- Boundary markers: Instructions state the "specification remains authoritative" but do not define explicit delimiters to isolate untrusted input.
- Capability inventory: The skill generates a plan containing "exact commands" and "global validation commands" for execution in subsequent steps (SKILL.md).
- Sanitization: No specific filtering or escaping mechanisms are described for processing the contents of the specifications.
Audit Metadata