release
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script located at
scripts/release.shand multiple command-line interface (CLI) tools includinggit,npm, andghto automate the release sequence. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided release notes and interpolates them into several commands, creating a surface for indirect prompt injection.
- Ingestion points: User-provided release messages are passed as arguments to the
scripts/release.shscript and manual commands inSKILL.md(e.g.,git commit -mandgh release create). - Boundary markers: The instructions do not define delimiters or apply safety warnings to the user-supplied content before it is processed by the shell.
- Capability inventory: The skill possesses the ability to execute shell scripts, commit and push code to remote repositories, and publish packages to npm as described in
SKILL.md. - Sanitization: There is no evidence of sanitization or validation applied to the external release notes before they are interpolated into commands.
- [COMMAND_EXECUTION]: The skill performs network operations using
npm publish,git push, andgh release createto upload code and release metadata to external services.
Audit Metadata