functional-tester
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown and CSV templates. There are no scripts (Python, JavaScript, Shell, etc.) or executable components provided within the skill package.
- [SAFE]: The instructions emphasize safe testing practices, explicitly directing the agent to run only authorized non-destructive checks and blocking tests that could affect production or secrets pending authorization.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process project documentation (architecture, requirements), which is an ingestion surface for untrusted data. However, the skill instructions include boundary markers and specific evaluation criteria that mitigate accidental obedience to instructions embedded in that data. The severity is low as it is a documentation-only framework.
- [METADATA_POISONING]: All metadata fields (name, description) accurately reflect the skill's purpose for functional testing and do not contain deceptive instructions.
Audit Metadata