linkedin-post
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious behavior, obfuscation, or persistence mechanisms were detected within the skill file.
- [Indirect Prompt Injection] (LOW): The skill interacts with external data sources. Evidence: 1. Ingestion points: Notion search and fetch tools specified in the 'Notion Integration' section. 2. Boundary markers: The skill utilizes rigid templates for output. 3. Capability inventory: The skill is limited to text generation and does not have file system or shell execution capabilities. 4. Sanitization: Specific '0 Finance' compliance rules act as a filter for prohibited language. The risk is minimal given the absence of dangerous tool capabilities.
Audit Metadata