grill-me

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is instructed to analyze potentially untrusted content from the user's repository, including source code, schemas, and documentation. This creates an attack surface where instructions embedded in these files (e.g., in code comments or documentation) could influence the agent's behavior during the interview process.
  • Ingestion points: Per SKILL.md, the agent is directed to 'Inspect code, tests, schemas, configuration, and documentation' found within the repository.
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore commands that may be contained within the analyzed repository files.
  • Capability inventory: The agent possesses the capability to read files from the repository and write log files to the local file system, specifically to ~/.engineering-workflow/ or user-defined paths.
  • Sanitization: The skill does not include mechanisms to sanitize or validate the content read from the repository files before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 07:10 PM