gitlab
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @useclawlink/cli, which fetches and executes the vendor's command-line interface from the NPM registry. This is the intended mechanism for the integration. - [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands to log in, connect to GitLab, and perform actions (e.g.,
npx @useclawlink/cli run gitlab). - [INDIRECT_PROMPT_INJECTION]: The skill acts on data retrieved from GitLab (such as issue content or project descriptions) and possesses write capabilities, creating a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: GitLab project data, group information, and issue details retrieved via the CLI in
SKILL.md. - Boundary markers: None present in the provided instructions.
- Capability inventory: GitLab write operations including creating projects, issues, branches, and deleting/archiving projects.
- Sanitization: No explicit sanitization or filtering of GitLab content is described in the skill.
Audit Metadata