alterlab-nmc-newsletter
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and workflow are focused entirely on newsletter editorial strategy and design. It does not contain any patterns indicative of prompt injection, unauthorized credential access, or malicious persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a standard surface for indirect prompt injection as it is designed to process untrusted external information.
- Ingestion points: The agent is instructed to search the web for industry benchmarks and trends, and to read project files for context (SKILL.md).
- Boundary markers: There are no specific boundary markers or 'ignore' instructions defined for the data ingested from search results or local project files.
- Capability inventory: The skill has the capability to perform web searches, read local files, and write new markdown files to the project directory.
- Sanitization: No explicit sanitization or filtering of external content is described before the data is used in the creation of newsletter drafts and blueprints.
Audit Metadata