The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli tool from the npm registry. This is a vendor-provided resource used for the skill's primary purpose.
[COMMAND_EXECUTION]: The instructions require the agent to execute multiple shell commands (e.g., npx @useclawlink/cli run gitlab ...) to perform repository management and data retrieval tasks.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves data from external sources (GitLab issues, project descriptions, and commit history) that could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Output from GitLab actions such as gitlab_get_group, gitlab_create_project_issue, and gitlab_get_commit_refs enter the agent's context.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill definition.
Capability inventory: The agent has the capability to perform high-impact actions in GitLab, including archiving projects, deleting projects, and creating groups via shell commands.
Sanitization: No sanitization or validation of the data returned from the GitLab API is defined before it is processed by the agent.

gitlab