workflow-hello-world

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structural instructions for the agent to use a 'meta-skill' (deepline-gtm) and load specific recipe files from a local directory. No malicious intent or suspicious commands were found.
  • [COMMAND_EXECUTION]: The skill instructs the agent to invoke the deepline-gtm tool. This appears to be a legitimate use of a vendor-provided tool for workflow automation.
  • [PROMPT_INJECTION]: The skill utilizes instructional language to guide agent behavior (e.g., 'Follow the meta-skill's full routing instructions'), but these do not attempt to bypass safety filters or override system constraints.
  • [DATA_EXFILTRATION]: There are no indicators of data collection or exfiltration. File access is restricted to relative paths for documentation (../deepline-gtm/recipes/).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:22 PM
Security Audit — agent-trust-hub — workflow-hello-world