gitlab
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
glabCLI tool via Bash to perform operations on GitLab repositories, issues, merge requests, and CI pipelines. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it retrieves and processes content from GitLab (such as issue descriptions, merge request comments, and repository files) which could be controlled by external actors.
- Ingestion points: Data enters the agent context through CLI commands like
glab issue view,glab mr view, andglab api(SKILL.md). - Boundary markers: The instructions do not define specific delimiters to separate untrusted GitLab content from agent instructions.
- Capability inventory: The skill is capable of executing Bash commands to modify GitLab resources, including creating notes and merging branches.
- Sanitization: The skill correctly employs
jqto URI-encode project paths and filenames during API interactions, mitigating shell command injection risks.
Audit Metadata