ci-runner-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- Command Execution: The skill and its associated script execute shell commands, specifically the GitHub CLI (
gh) and a pre-flight setup utility. These commands are constructed using structured argument lists, which is a standard practice to prevent command injection. - External Data Ingestion: The script fetches workflow configuration files directly from GitHub's raw content servers for analysis. This ingestion point is managed by explicit instructions in the skill that direct the agent to treat the content strictly as data, mitigating potential indirect prompt injection risks.
- Secure Data Parsing: The analysis script utilizes
yaml.safe_loadto process workflow files. This ensures that untrusted YAML configuration content cannot trigger unintended code execution during the parsing phase.
Audit Metadata