add-unit-tests

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses dynamic context injection via the exclamation-backtick syntax to run 'date' and 'go version' when the skill is loaded. These are informational environment commands and do not demonstrate malicious behavior.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by processing untrusted feature specifications.
  • Ingestion points: User-provided file paths or currently selected text as defined in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: Reading local files, writing new test files, and executing shell commands to run test suites.
  • Sanitization: The skill does not perform validation or escaping on the ingested requirement text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:10 AM
Security Audit — agent-trust-hub — add-unit-tests