skills/openhands/extensions/gitlab/Gen Agent Trust Hub

gitlab

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill provides instructions to update the Git remote URL with the GITLAB_TOKEN environment variable (e.g., git remote set-url origin https://oauth2:${GITLAB_TOKEN}@gitlab.com/...). This practice results in the sensitive authentication token being stored in plain text in the .git/config file on the local filesystem, where it may be exposed to other users or processes.
  • [COMMAND_EXECUTION]: The skill relies on shell commands, including git and curl, to manage code repositories and interact with the GitLab API.
  • [PROMPT_INJECTION]: The skill facilitates an attack surface for indirect prompt injection (Category 8).
  • Ingestion points: Data retrieved from the GitLab API or repository content via curl and git commands (SKILL.md).
  • Capability inventory: Execution of shell commands (git, curl) to perform repository operations (SKILL.md).
  • Boundary markers: There are no boundary markers or specific instructions provided to the agent to distinguish between its instructions and potentially malicious data fetched from external sources.
  • Sanitization: No sanitization or validation mechanisms are described for processing data received from the GitLab environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:58 PM
Security Audit — agent-trust-hub — gitlab