The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes data from external sources (GitLab issues, merge requests, and commits) that could contain malicious instructions.
Ingestion points: Data enters the context through tools such as GITLAB_LIST_PROJECT_ISSUES, GITLAB_GET_PROJECT_MERGE_REQUESTS, and GITLAB_LIST_REPOSITORY_COMMITS as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided data from potentially malicious content within GitLab records.
Capability inventory: The skill has significant write capabilities including GITLAB_CREATE_PROJECT_ISSUE, GITLAB_UPDATE_PROJECT_ISSUE, and GITLAB_CREATE_REPOSITORY_BRANCH as listed in the workflows.
Sanitization: No sanitization or validation logic is specified for handling external data before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill setup requires the user to configure an external MCP server at https://rube.app/mcp. This is a known service endpoint for the Rube/Composio platform used to execute the described GitLab tools.
[SAFE]: The skill consists of instructional documentation for standard DevOps automation. No evidence of obfuscation, hardcoded credentials, malicious persistence, or unauthorized system access was found.

gitlab-automation