dependabot-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses dynamic context injection to identify the repository context when the skill is loaded. * Evidence: The SKILL.md file contains:
!gh repo view --json nameWithOwner -q .nameWithOwner 2>/dev/null || echo "(unknown — run from inside the repo)"``. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external pull requests and changelogs, creating a surface for indirect prompt injection. * Ingestion points: PR titles, descriptions, and diffs via gh pr view/diff, and changelogs via WebFetch. * Boundary markers: Not present. * Capability inventory: The agent can execute shell commands and post PR comments. * Sanitization: Not present.
- [EXTERNAL_DOWNLOADS]: The skill fetches information from trusted developer platforms and package registries. * Evidence: Accesses github.com and rubygems.org for changelog and release information.
Audit Metadata