dagu-rest-api

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent constraints were found.
  • [Data Exposure & Exfiltration] (SAFE): The skill interacts with local or internal server addresses (localhost:8080). No evidence of credential exposure or unauthorized data transmission to external domains was identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill utilizes standard tools such as the curl utility and the Python requests library. No remote script execution or installation of suspicious packages was observed.
  • [Command Execution] (SAFE): API operations to trigger or modify workflows are part of the intended Dagu functionality and do not represent unauthorized local command execution on the host system.
  • [Indirect Prompt Injection] (SAFE): While the skill involves reading workflow logs and statuses which are external data sources, no malicious instructions targeting the agent were found in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 04:25 PM