check-upstream-updates
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands including npm view, gh release list, gh api, gh label create, gh issue create, and grep. These are used to gather dependency information, check for code impact, and track findings via GitHub issues.
- [EXTERNAL_DOWNLOADS]: Fetches metadata and release content from NPM and GitHub repositories. These operations target well-known and trusted platforms for software development.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external sources. 1. Ingestion points: Upstream release notes from gh release list, CHANGELOG.md files, and GitHub API responses. 2. Boundary markers: No explicit markers are defined to delimit external content. 3. Capability inventory: The skill can create GitHub labels and issues. 4. Sanitization: No explicit sanitization or validation of the retrieved release notes is performed before they are interpolated into issue templates.
Audit Metadata