agentos-api-workflows
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill facilitates the transmission of user-provided data to a remote API endpoint. This is the intended function of the tool.
- [PROMPT_INJECTION]: The skill ingests and displays remote API data (workflow metadata and run results), creating a surface for indirect prompt injection. Ingestion points: scripts/run_workflows.py. Boundary markers: None. Capability inventory: Network requests and console output. Sanitization: None.
- [SAFE]: A metadata discrepancy in the author field was identified but is considered a non-malicious branding inconsistency.
Audit Metadata