skills/amit-t/skills/grill-me-auto/Gen Agent Trust Hub

grill-me-auto

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the local repository, such as documentation, Architecture Decision Records (ADRs), and commit history, to generate its "grill" questions. This data could contain malicious instructions designed to manipulate the agent's behavior or the content of the generated document.
  • Ingestion points: Step 1 in SKILL.md explicitly instructs the agent to read repository files, CONTEXT.md, ADRs, docs, and recent commits.
  • Boundary markers: The skill does not define clear delimiters or "ignore" instructions for the ingested context, increasing the risk that the agent might follow instructions embedded in these files.
  • Capability inventory: The skill has the capability to read files across the project, write new files to the .grills/ directory, and perform git operations (like staging changes to .gitignore).
  • Sanitization: There is no evidence of sanitization or filtering of the repository content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill uses shell commands for project environment discovery and basic configuration management.
  • Evidence: It executes git rev-parse --show-toplevel to locate the project root and modifies the .gitignore file to exclude the generated .grills/ directory, staging the change with git add.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:18 AM