git-release-start
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
git,gh(GitHub CLI), andglab(GitLab CLI) to perform operations such as creating remote branches, fetching updates, and committing local changes. These are standard tools for release management. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of data from external repositories. 1. Ingestion points: Data is ingested from
git branch -r,git log, andgit ls-remoteinSKILL.md. 2. Boundary markers: The skill lacks explicit boundary markers or instructions to ignore potentially malicious content embedded in branch names or commit messages. 3. Capability inventory: The skill can execute API calls viaghandglab, performgit push, and write to local files inSKILL.md. 4. Sanitization: There is no evidence of sanitization or validation of the branch names or commit messages retrieved from the remote repository before they are used in subsequent commands.
Audit Metadata