glab-api
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with GitLab API endpoints that return user-generated content, such as issue descriptions and commit messages, which could harbor indirect prompt injection attacks.
- Ingestion points: REST and GraphQL API responses from GitLab (e.g., projects, issues, releases).
- Boundary markers: The skill includes an explicit 'Security Note' advising the agent to treat fetched content as data only and to avoid following embedded instructions.
- Capability inventory: Authenticated network access to GitLab and the ability to read local files via command-line flags.
- Sanitization: There is no mention of automated sanitization or filtering for the data retrieved from external sources.
- [COMMAND_EXECUTION]: The skill instructs the agent on how to execute 'glab api' commands to manage GitLab resources.
- Usage: Supports REST and GraphQL requests, including pagination and file uploads.
- Data handling: Supports reading local files using the '@' prefix in flags like '--field' or '--form', which transmits file contents to the GitLab API.
Audit Metadata