skill-tester-ci
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands to perform validation, including
gh aw compilevia the GitHub CLI and a local Python validation script (quick_validate.py). - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from repository files. An attacker who can commit to the repository could potentially influence the validation logic or compiler behavior, though the script is designed for local developer use and structural verification.
- Ingestion points: Reads files from the
skills/directory, specifically*-cifolders and theirreferences/workflow-example.mdfiles. - Boundary markers: None identified.
- Capability inventory: Uses
gh aw compileandpython3to validate and compile workflow blocks. - Sanitization: No specific sanitization or escaping of file content is performed before processing.
Audit Metadata