release
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to run workflows, list runs, and create pull requests or releases. It also usesnpmfor distribution tag management andgitfor tag discovery. - [COMMAND_EXECUTION]: Uses
node -pto evaluate JavaScript for extracting theversionfield from localpackage.jsonfiles. - [PROMPT_INJECTION]: The skill processes content from
CHANGELOG.mdfiles, which is a potential surface for indirect prompt injection. - Ingestion points: Package-specific
CHANGELOG.mdfiles. - Boundary markers: None; uses
awkto extract text between version headers. - Capability inventory: Includes shell command execution (
gh,npm,node) and GitHub API interactions. - Sanitization: None; the extracted changelog text is passed directly to the
gh release createcommand.
Audit Metadata