avoid-ai-writing
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety filters were detected. The instructions focus exclusively on text-editing tasks.
- [EXTERNAL_DOWNLOADS]: The skill does not download or execute external code. It contains a reference to a GitHub repository for research purposes, but no fetching or execution occurs.
- [DATA_EXFILTRATION]: No network operations, sensitive file path access, or credential harvesting patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill operates by processing untrusted user text for rewriting. While this represents a data ingestion surface, the skill lacks any capabilities (such as network access, file system writes, or command execution) that could be exploited by instructions embedded in the processed text.
- [DYNAMIC_CONTEXT_INJECTION]: No use of shell command execution at load time (dynamic context syntax) was detected.
Audit Metadata