blog-post-writer
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves data from external web sources to inform its writing process.
- Evidence: Fetches recent blog posts from
https://nicknisi.com/postsand 'words to watch' from the Wikipedia API. - Context: These interactions are used for style calibration and quality control. The domains involved are either vendor-owned (nicknisi.com) or well-known public services (wikipedia.org).
- [PROMPT_INJECTION]: The skill is subject to a surface for indirect prompt injection due to its ingestion of external content.
- Ingestion points: Loads user-provided 'brain dumps' and content from external websites (nicknisi.com, wikipedia.org) into the agent context.
- Boundary markers: No explicit delimiters are used in the prompt to separate external data from system instructions.
- Capability inventory: The skill is restricted to text generation and does not have access to command execution, file system modifications, or sensitive local data.
- Sanitization: No explicit sanitization of the external content is performed before it is processed by the model.
- Context: This risk is considered negligible given the trusted nature of the primary external sources and the limited, text-only capabilities of the skill.
Audit Metadata