skills/dydoc/skills/grill-with-docs/Gen Agent Trust Hub

grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill functions by interviewing users about their plans or designs to generate Architecture Decision Records (ADRs) and glossaries. This creates a surface for indirect prompt injection if the user-supplied content contains instructions meant to manipulate the agent's behavior during document generation.
  • Ingestion points: The skill body indicates it processes user plans and designs provided during the grilling process.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the input data.
  • Capability inventory: The skill creates documentation files (ADRs and glossaries), implying file system write capabilities.
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the incoming design data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:28 AM
Security Audit — agent-trust-hub — grill-with-docs