grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans, decisions, or ideas to generate or update project documentation like
CONTEXT.mdand Architectural Decision Records (ADRs). This introduces a potential surface for indirect prompt injection if the input contains malicious instructions designed to influence the agent's behavior or corrupt the documentation. - Ingestion points: The skill accepts a 'plan, decision, or idea' as the primary input via the
argument-hint. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definition.
- Capability inventory: The skill is designed to capture terms and decisions by writing to local markdown files (
CONTEXT.md, ADRs). - Sanitization: There are no instructions provided for sanitizing or validating the content before it is processed or written to the documentation.
Audit Metadata