substack-note
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured templates and writing guidelines for generating Substack notes. Its functionality is limited to content creation based on the provided instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect injection as it processes external data. Ingestion points: Context profiles (/context/voice-dna.json, /context/icp.json, /context/business-profile.json) and knowledge base files (/knowledge/). Boundary markers: None present. Capability inventory: Standard text generation and context retrieval; no high-risk capabilities like network access or shell execution are utilized. Sanitization: None observed. This data ingestion is integral to the skill's primary purpose of providing tailored content generation.
Audit Metadata