github-workflow-automation
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes automation logic from vendor-owned packages
ruv-swarmandclaude-flowusing thenpxutility. - [COMMAND_EXECUTION]: Utilizes the GitHub CLI (
gh) and Git to perform repository operations such as creating issues, managing pull requests, and viewing workflow logs. - [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection due to the processing of external repository data.
- Ingestion points: The skill reads external content through
gh pr viewfor pull request files and metadata (line 242) and monitors workflow run outputs (line 197). - Boundary markers: No specific delimiters or instructions to ignore embedded directives within processed content were observed in the workflow templates.
- Capability inventory: Capabilities include the ability to create and comment on GitHub issues and pull requests, as well as orchestrating multi-agent tasks via the
ruv-swarmframework. - Sanitization: Content is parsed using
jqto extract specific fields, but the extracted text is subsequently used in automated coordination and reporting tasks without additional filtering or escaping.
Audit Metadata