tests-run-all-tests
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a high-level orchestrator that delegates tasks to other internal skills. It does not perform any sensitive operations directly.
- [COMMAND_EXECUTION]: Although 'Bash' is listed in the 'allowed-tools' section, the skill instructions do not utilize it for executing arbitrary or suspicious commands; it primarily focuses on task orchestration and report compilation.
- [PROMPT_INJECTION]: No evidence of prompt injection, instruction overrides, or safety bypass attempts was found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes outputs from other skills ('tests-local-run-local-tests' and 'tests-prod-run-prod-tests') to create a summary. While this presents a theoretical surface for indirect injection if the sub-skills' outputs are untrusted, the intended use case involves internal project testing, making the risk negligible in this context.
Audit Metadata