glab-api

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated content from GitLab such as issue bodies and commit messages which may contain malicious instructions.
  • Ingestion points: GitLab API responses.
  • Boundary markers: Explicit security warning included in the documentation header.
  • Capability inventory: Network access via API and arbitrary local file reading via tool flags.
  • Sanitization: No specific data sanitization or filtering logic is specified.
  • [DATA_EXFILTRATION]: The documentation for --field, --raw-field, and --form flags highlights a magic syntax using the @ symbol to read content from local files. This provides a mechanism for the agent to access and send sensitive local data (e.g., credentials or configuration files) over the network if manipulated by a malicious prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 07:07 PM
Security Audit — agent-trust-hub — glab-api