detect-bullshit-tests

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the repository's test files.
  • Ingestion points: The skill reads the content of test files identified via git diff or direct user pointers in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore instructions embedded within the analyzed test code.
  • Capability inventory: The skill performs file system reads and uses shell commands (git diff) to identify targets.
  • Sanitization: No sanitization of the content of the test files is specified before processing.
  • [COMMAND_EXECUTION]: The skill uses git diff to identify changed files. This is a standard use of developer tools and is restricted to metadata (file names) rather than code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 02:40 PM
Security Audit — agent-trust-hub — detect-bullshit-tests