alterlab-nmc-newsletter
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a content strategist. It performs standard file reading and web searching tasks associated with its primary purpose of creating newsletter drafts and blueprints.
- [DATA_EXPOSURE_AND_EXFILTRATION]: While the skill reads local project files and performs web searches, these actions are scoped to the intended use case of gathering context for newsletter creation. No unauthorized exfiltration or credential harvesting patterns were observed.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the web and local project files (e.g., brand guidelines, audience research). 1. Ingestion points: Web searches and local project files (SKILL.md workflow section). 2. Boundary markers: Absent. 3. Capability inventory: Web search, file read, and file write operations. 4. Sanitization: Absent.
Audit Metadata