glab-stack
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of the
glabcommand-line tool to manage GitLab merge requests and Git branches. This functionality is the intended primary purpose of the skill and is documented for developer use. - [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection because it processes data from Git commit messages and GitLab merge requests (ingestion points). The capability inventory includes executing
glabcommands and writing to local metadata directories in SKILL.md. While boundary markers and explicit sanitization are not mentioned, the risk is characteristic of tools interacting with collaborative developer data and is considered safe within the intended use case.
Audit Metadata