edge-cases
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied PRDs as untrusted input.
- Ingestion points: The skill reads a provided PRD thoroughly (SKILL.md).
- Boundary markers: None specified to differentiate input data from instructions.
- Capability inventory: None detected across the skill body (SKILL.md); the skill only generates text output and does not have access to tools or system commands.
- Sanitization: No input sanitization is performed on the ingested text.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include scripts, binaries, or configuration files that execute code.
Audit Metadata