release-and-auto-changelog
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several shell commands to manage repository state, including staging all current changes (
git add -A), creating annotated tags, and pushing updates to the remotemainbranch and tags. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the GitHub API to generate documentation, which creates a potential surface for indirect prompt injection if the source repository contains malicious release notes.
- Ingestion points: Fetches release data from an external source via
gh api repos/{owner}/{repo}/releases. - Boundary markers: None; the external content is processed and written directly to the changelog.
- Capability inventory: The skill has the ability to write to the file system, commit changes, and push to remote repositories.
- Sanitization: The
scripts/generate_changelog.jsscript performs no escaping or sanitization of ther.body(release notes) field before outputting it toCHANGELOG.md.
Audit Metadata