linkedin-post
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidance for content creation and includes explicit instructions for maintaining regulatory compliance, which is a safety-positive feature.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Notion to inform its drafting process. Although this creates a potential surface for indirect prompt injection if the source data were malicious, the functionality is standard for this type of agent skill.
- Ingestion points: Data is retrieved from Notion search results and specific document IDs (SKILL.md).
- Boundary markers: None explicitly defined in the tool usage instructions.
- Capability inventory: The skill uses Notion search and fetch tools and text generation; it has no capabilities for code execution or system modification.
- Sanitization: No specific sanitization of external data is noted in the instructions.
Audit Metadata