blog-post-writer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a purely instructional text-processing tool. It reads local reference files for style and structure and applies these to user-provided input without the need for high-risk capabilities.
- [SAFE]: No network operations, credential access, or sensitive file interactions were detected. The skill's scope is restricted to the local file bundle and prompt-based text generation.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user data. Ingestion points: User-provided 'brain dump' content processed in SKILL.md. Boundary markers: No specific delimiters are defined to separate instructions from user input. Capability inventory: No high-risk tools (shell, filesystem, network) are authorized or utilized. Sanitization: The skill does not perform explicit sanitization of the input data. Risk assessment: The absence of active capabilities prevents any escalation from potential injection; the impact is limited to the text generation output.
Audit Metadata