qa-expert

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides documentation on using shell commands to identify test-related patterns in codebases.
  • Evidence: Bash snippets in SKILL.md demonstrating recursive searches using grep for terms like 'test', 'assert', and 'describe' within source and test directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external files (code and tests), which acts as an ingestion point for potentially untrusted data that could contain hidden instructions for the agent.
  • Ingestion points: Reads files from 'tests/' and 'src/' directories via the grep command patterns described in the 'Quality Assurance Processes' section.
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to disregard potential instructions found within the analyzed files.
  • Capability inventory: The skill utilizes file search capabilities via grep on the local file system.
  • Sanitization: There is no evidence of sanitization or filtering of the content found within the files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 08:06 AM
Security Audit — agent-trust-hub — qa-expert