lovstudio-fact-check
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instruction-based and does not contain any scripts, executables, or binary files.
- [NO_CODE]: The skill is declared as an 'instruction-only' skill, minimizing the risk of remote code execution or persistence.
- [PROMPT_INJECTION]: The skill processes external claims which are inherently untrusted.
- Ingestion points: The user provides a claim or text to be fact-checked.
- Boundary markers: The agent is instructed to restate the claim as a verifiable proposition and evaluate it using a specific evidence framework.
- Capability inventory: The skill relies on web/search access to retrieve evidence.
- Sanitization: No explicit content sanitization is described, but the analytical process requires independent verification of all data points.
Audit Metadata