generic-writing-detector
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prose and novel passages, creating an ingestion point for data that could contain malicious instructions designed to influence the agent's behavior (SKILL.md). The instructions do not define boundary markers or delimiters to separate user text from instructions, nor do they include sanitization or filtering logic. However, the skill lacks dangerous capabilities such as network access, file-writing, or subprocess execution, which significantly mitigates the potential impact of an injection.
- [SAFE]: No malicious patterns, obfuscation, hardcoded credentials, or unauthorized persistence mechanisms were identified. The skill's functionality is strictly limited to text analysis and stylistic critique.
Audit Metadata