jb-local-release
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes command-line tools including git, gh, and various Node.js package managers (npm, pnpm, yarn, bun) to automate release tasks such as committing changes, tagging versions, and pushing to remote repositories. It also executes scripts defined in the repository's package.json file for verification steps like linting and testing.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes instructions found in repository files to guide the release workflow.\n
- Ingestion points: The skill reads local project files including AGENTS.md, CLAUDE.md, README.md, CONTRIBUTING.md, and CHANGELOG.md (SKILL.md).\n
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided when reading these files.\n
- Capability inventory: The skill possesses high-privilege capabilities including file system writes, shell command execution via package managers, and remote repository pushes.\n
- Sanitization: There is no evidence of sanitization or validation of the content ingested from the project files before processing.
Audit Metadata