grilling
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process arbitrary user-supplied plans or ideas and use them to drive autonomous exploration of the local environment.
- Ingestion points: User-provided plans, decisions, or ideas ingested via instructions in
SKILL.md. - Boundary markers: None identified; the skill does not use specific delimiters or instructions to prevent the agent from obeying instructions embedded in the user's plan.
- Capability inventory: The skill explicitly authorizes the agent to access the filesystem and use tools to find 'facts' related to the user's input.
- Sanitization: No validation or sanitization of external content is specified before the agent interpolates the user's plan into its search and tool-use logic.
Audit Metadata