bump-version

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Git commands (git add, git commit, git tag, git push) to automate repository updates and version tagging. These are expected behaviors for a versioning utility.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from local userscript files which could potentially lead to indirect prompt injection. 1. Ingestion points: Reads .user.js and README.md files to extract version and documentation data. 2. Boundary markers: No delimiters or ignore instructions are used for the ingested content. 3. Capability inventory: Executes Git commands through the shell. 4. Sanitization: No explicit validation or escaping is performed on strings extracted from files before they are interpolated into Git command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:52 AM
Security Audit — agent-trust-hub — bump-version