release-bump

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill relies on the bumpversion utility, which is a common Python package for managing versioning. It suggests installation via pip.
  • [COMMAND_EXECUTION]: The skill uses several shell commands including git (status, add, show, tag), grep, and bumpversion to perform repository management tasks. These operations are restricted to the local workspace and are necessary for the skill's functionality.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill generates GitHub comparison URLs pointing to the author's own repository (github.com/jamiepine/voicebox). These are standard informational links for changelog entries.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the CHANGELOG.md file, which is an attack surface for indirect prompt injection. However, the risk is minimal as the skill performs only text substitution and git staging without interpreting the content as instructions. * Ingestion points: CHANGELOG.md. * Boundary markers: Markdown headers like ## [Unreleased]. * Capability inventory: File system modifications and Git operations. * Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 01:59 AM
Security Audit — agent-trust-hub — release-bump