odyssey4me/github
Create and manage GitHub issues, pull requests, workflows, and repositories using the gh CLI. Use when asked to open a PR, merge a pull request, check repo actions, list issues, create a branch, or manage GitHub projects.
64
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill's SKILL.md and scripts/github.py explicitly run gh CLI commands (e.g., gh issue view, gh pr view, gh search, gh run view) to fetch and format public GitHub issues, PRs, comments and repo content (user-generated/untrusted) for the agent to read and act on, which could allow indirect prompt-injection from that third-party content.
Where we found it
github.com
domain · 39 sites
The plugin uses the gh CLI to fetch user-generated content (issues, PRs, comments, workflow runs, repository data, search results) from GitHub's API, which is then formatted and returned to the agent for consumption. This third-party content could contain prompt-injection payloads.
- Audited
- Security analysis