github-integration
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it retrieves and processes content from external GitHub issues and pull requests.
- Ingestion points: Data is fetched via the GitHub API in
scripts/github_issue.pyandscripts/github_pr.py, specifically issue/PR titles and bodies which are then presented to the agent. - Boundary markers: No delimiters or instructions are provided in
SKILL.mdto help the agent distinguish between its core instructions and the potentially untrusted data fetched from GitHub. - Capability inventory: While the skill can perform network operations via the GitHub API and execute its own scripts, it does not have access to dangerous system-level functions like arbitrary code execution or local file system writes.
- Sanitization: The skill does not implement any validation or sanitization of the content retrieved from GitHub before passing it into the agent's context.
Audit Metadata