consort-check
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill is designed to process untrusted manuscript data. While this represents an ingestion surface, the skill has no dangerous capabilities (no network access, no file writing, and no command execution), rendering the risk negligible. \n
- Ingestion points: Manuscript text processed in Workflow step 1. \n
- Boundary markers: Absent. \n
- Capability inventory: None. \n
- Sanitization: Absent. \n- [Unverifiable Dependencies] (SAFE): No Python or Node.js packages are required or installed. \n- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or network exfiltration patterns were detected. \n- [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override system prompts were found. \n- [Obfuscation] (SAFE): No Base64, zero-width characters, or homoglyphs were detected.
Audit Metadata