bypass-sapling
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill instructions.
- [EXTERNAL_DOWNLOADS]: The skill references the @rephrasy/mcp NPM package and the rephrasy.ai domain. These are legitimate resources owned by the skill author ('rephrasyai') used for the skill's stated purpose of text humanization.
- [INDIRECT_PROMPT_INJECTION]: The skill functions by processing user-provided text for rewriting. This represents a standard ingestion surface for text-manipulation tasks; no specific exploitable patterns or autonomous execution risks were identified in the instructions.
Audit Metadata