tests-local-run-local-tests
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a high-level orchestrator for internal testing tasks. It does not contain any executable code, obfuscation, or sensitive data access.
- [PROMPT_INJECTION]: The skill has an indirect injection surface because it aggregates outputs from sub-skills into a final report. 1. Ingestion points: Output from tests-local-test-and-update-internal-links and tests-local-test-local-site-links. 2. Boundary markers: Not explicitly used in the instructions for result aggregation. 3. Capability inventory: The skill lists Bash and Task in its allowed tools. 4. Sanitization: None. This is a common pattern for coordinator skills and is considered safe in this context.
Audit Metadata