reusable-workflow-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources as its core function. 1. Ingestion points: CI/CD configuration files (e.g., .gitlab-ci.yml, Jenkinsfile) are parsed from various platforms during discovery. 2. Boundary markers: The instructions lack specific delimiters or instructions to ignore natural language content embedded within the source configuration files. 3. Capability inventory: The skill is authorized to search repositories via mcp_github_search_repositories and write .yml and .md files. It has no arbitrary command execution or network exfiltration capabilities. 4. Sanitization: There is no mention of sanitizing or validating external configuration data before it is processed for pattern extraction.
- [EXTERNAL_DOWNLOADS]: The provided workflow templates reference official GitHub Actions from the actions organization. Evidence: The template uses actions/checkout@v4 and actions/setup-node@v4.
Audit Metadata