skills/benjaming/ai-skills/ci-watch/Gen Agent Trust Hub

ci-watch

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes common command-line utilities (git, gh, prettier, eslint) to perform expected repository management tasks. The workflow is transparent and restricted to the user's authenticated environment.\n- [COMMAND_EXECUTION]: The skill invokes commands that modify the repository state, such as git push and git rebase. These operations are well-defined and essential for automated CI resolution as described.\n- [PROMPT_INJECTION]: The skill ingests branch names and PR status from GitHub, creating a surface for indirect prompt injection. The impact is mitigated by the deterministic nature of the instructions and the scope of the available tools.\n
  • Ingestion points: PR and branch metadata retrieved via gh pr view in SKILL.md.\n
  • Boundary markers: None present.\n
  • Capability inventory: Git write operations, PR state changes, and linting tools found in SKILL.md.\n
  • Sanitization: None detected for external data strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 11:39 AM
Security Audit — agent-trust-hub — ci-watch