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 compile via 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 *-ci folders and their references/workflow-example.md files.
  • Boundary markers: None identified.
  • Capability inventory: Uses gh aw compile and python3 to validate and compile workflow blocks.
  • Sanitization: No specific sanitization or escaping of file content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:41 AM
Security Audit — agent-trust-hub — skill-tester-ci