version-bump-cx
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests git commit history to automate documentation updates and changelog generation.
- Ingestion points: Git commit messages collected via
git login Phase 2, Step 4 ofSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the commit messages it reads.
- Capability inventory: The agent has the ability to run
npm install(Step 9),npm test(Step 13), andgit commit(Step 16), as well as perform file writes and modifications usingsed -i. - Sanitization: The instructions ask the agent to rewrite commit messages into human-readable descriptions, which relies on the LLM's interpretation rather than technical sanitization or escaping of the input data.
- [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to perform maintenance tasks and verify project state.
- Evidence: The skill utilizes
npm version,sed -i,npm install,npm test, andgit commitcommands to automate the versioning workflow across multiple files and packages.
Audit Metadata