grilling
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to autonomously retrieve facts from the environment, including reading source code, documentation, and tickets. This creates a surface for indirect prompt injection where malicious instructions embedded in those files could influence the agent's behavior.
- Ingestion points: Primary artifacts (source code, docs, tickets, prototypes) as specified in SKILL.md.
- Boundary markers: None specified for external content.
- Capability inventory: Filesystem access and sub-agent dispatch for environmental lookups.
- Sanitization: No explicit sanitization or filtering of retrieved content is mentioned.
Audit Metadata