watch-github-actions
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard
ghandgitcommands to interact with GitHub repositories and Actions. All commands are used for their intended purpose of checking workflow status and logs without excessive privileges. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection when viewing workflow logs via
gh run view --log, as it ingests untrusted data from build outputs. This is an inherent property of monitoring tools that process external content and does not represent a malicious instruction within the skill itself.
Audit Metadata