github-ops
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform repository operations such as editing issues, commenting, and managing releases. - Evidence: Commands like
gh issue edit,gh pr checks, andgh release createare used throughoutSKILL.mdto automate GitHub workflows. - [EXTERNAL_DOWNLOADS]: The skill interacts with external GitHub APIs to retrieve repository data and CI logs.
- Evidence: Uses
gh apiandgh run view --log-failedto fetch data from GitHub's infrastructure. - [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from GitHub issues and pull requests, creating a surface for indirect prompt injection.
- Ingestion points: GitHub issue titles, bodies, comments, and PR metadata (found in
SKILL.md). - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in the ingested GitHub content.
- Capability inventory: The skill can execute various write operations via the
ghCLI, including commenting, labeling, and rerunning workflows. - Sanitization: Absent; the skill does not specify validation or sanitization for the content read from GitHub.
Audit Metadata