cria-prd
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from users and web searches which could potentially contain malicious instructions.
- Ingestion points: User-provided feature requests (Step 2) and external business rule data from Web Search (Step 3) in SKILL.md.
- Boundary markers: Not present; the skill does not use specific delimiters to separate external data from its core instructions.
- Capability inventory: Includes the ability to write files to the local directory (Step 5) and perform network searches.
- Sanitization: No explicit logic is defined to sanitize or validate the content of the user input or search results before document generation.
Audit Metadata