syndly-draft

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external capture text and user input which could contain malicious instructions. 1. Ingestion points: Workflow Steps 1 and 2 ingest untrusted data. 2. Boundary markers: Workflow Step 2 instructs the agent to treat text as source data rather than instructions. 3. Capability inventory: Tools defined in the syndly-mcp block provide post creation and scheduling functionality. 4. Sanitization: Workflow Step 3 requires manual user approval of the draft before tool execution.
  • [SAFE]: No indicators of malicious activity, obfuscation, or security violations were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 08:24 AM
Security Audit — agent-trust-hub — syndly-draft