skills/bostonaholic/team/version-bump/Gen Agent Trust Hub

version-bump

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands including git, gh, grep, sed, and jq to manage repository state. It also runs local project scripts (.claude/scripts/version-bump-required.sh, next-version.sh, check-version-consistency.sh) to perform versioning logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the repository's files and command outputs, creating a surface for indirect prompt injection.
  • Ingestion points: Reads from CHANGELOG.md, package.json, plugin.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json, .codex-plugin/plugin.json, .cursor-plugin/plugin.json, and gh repo view output.
  • Boundary markers: No specific delimiters or safety warnings are provided to separate project-controlled content from agent instructions.
  • Capability inventory: Shell command execution (bash, git, gh, sed, grep), file modification, and PR title editing.
  • Sanitization: Implements simple dot-escaping for version strings in regex, but does not sanitize content extracted from the changelog for release notes.
  • [DYNAMIC_EXECUTION]: Uses node -e with a static script to validate the integrity and syntax of multiple JSON manifest files before committing changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 12:09 AM