manage-artifacts

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard administrative toolset for Harness Artifact Registry using specific MCP tools (harness_list, harness_create). It contains no evidence of prompt injection, obfuscation, or persistence mechanisms.
  • [DATA_EXPOSURE]: The skill uses placeholders (e.g., <organization>, <project>) for sensitive identifiers and explicitly advises using CI/CD service accounts instead of personal credentials for push access.
  • [COMMAND_EXECUTION]: Resource creation and management are handled through defined MCP tool calls rather than arbitrary shell commands, minimizing the risk of command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:57 AM
Security Audit — agent-trust-hub — manage-artifacts