release-skills

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates repository management by executing shell commands for git and the GitHub CLI.
  • [COMMAND_EXECUTION]: It provides a mechanism for running arbitrary shell commands via release.hooks defined in the project configuration file .releaserc.yml.
  • [DATA_EXFILTRATION]: The skill pushes repository data and version information to external remote origins using git push.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted inputs from git logs and pull requests. 1. Ingestion points: Untrusted data from git log and gh pr view. 2. Boundary markers: No markers or warnings are used to delimit untrusted content. 3. Capability inventory: File system modification, arbitrary hook execution, and git network operations. 4. Sanitization: No validation or filtering is performed on external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 10:59 AM