github-project-management
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npxto download and execute software packages (ruv-swarmandclaude-flow) from the npm registry at runtime. - [COMMAND_EXECUTION]: Relies on the GitHub CLI (
gh) and shell utilities likejqto automate various project management tasks, including issue creation and board updates. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from GitHub.
- Ingestion points: The skill retrieves issue titles, descriptions, and comments using
gh issue viewandgh issue list. - Boundary markers: Ingested content is processed without explicit delimiters or instructions to the AI to ignore potentially malicious embedded commands.
- Capability inventory: The skill has the authority to modify repository state, including creating and editing issues, posting comments, and managing project board configurations.
- Sanitization: There is no evidence of content sanitization or validation before the data is analyzed and acted upon by the coordination agents.
Audit Metadata