github-project-management
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands and GitHub CLI (
gh) operations to manage repository issues, project boards, and milestones. - [EXTERNAL_DOWNLOADS]: Uses
npxto dynamically fetch and execute theruv-swarmandclaude-flowpackages. These are resources belonging to the skill's authoring ecosystem. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted data from GitHub.
- Ingestion points: Content is retrieved from GitHub via
gh issue view,gh issue list, andgh project item-listcommands. - Boundary markers: There are no instruction-ignoring delimiters or boundary markers used when interpolating issue titles, bodies, or comments into the agent's context.
- Capability inventory: The skill possesses capabilities to create, edit, comment on, and close GitHub issues, as well as execute shell scripts and manipulate project boards.
- Sanitization: The skill does not appear to sanitize or validate the content retrieved from GitHub before processing it with AI agents or using it in subtask decomposition.
Audit Metadata