grilling
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided plans and decisions, creating a surface for indirect instructions to influence agent behavior.- Ingestion points: User-supplied plans, ideas, or decisions described in the SKILL.md workflow.- Boundary markers: No explicit delimiters or ignore embedded instructions directives are present to separate user content from system instructions.- Capability inventory: The skill instructions explicitly direct the agent to dispatch sub-agents to explore the filesystem and environment tools to gather facts (SKILL.md).- Sanitization: There is no evidence of input validation, escaping, or filtering for the data ingested from the user or the environment.
Audit Metadata