test-desiderata

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's workflow instructs the agent to run the project's test suite, which involves executing code located within the repository's test files.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes content from the repository, creating a potential surface for indirect prompt injection.
  • Ingestion points: Test files and configuration files (e.g., package.json, pytest.ini) read from the repository as specified in SKILL.md.
  • Boundary markers: Absent in SKILL.md; the instructions do not specify the use of delimiters or 'ignore' instructions for the data being analyzed.
  • Capability inventory: Shell command execution (to run the test suite) and file system write access (to save reports to docs/test-quality-report.md) are mentioned in SKILL.md.
  • Sanitization: Absent in SKILL.md; the content from files is processed without explicit validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 03:07 PM