bypass-content-at-scale
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and rewrite user-supplied text drafts, which creates a vulnerability to indirect prompt injection if the input text contains malicious instructions.
- Ingestion points: User-provided text content provided for humanization.
- Boundary markers: The skill does not provide instructions to use delimiters or ignore instructions embedded in the user text.
- Capability inventory: The skill references humanization tools and models but does not contain direct file system or network execution logic within the SKILL.md file.
- Sanitization: No evidence of input validation or sanitization is present in the instructions.
- [EXTERNAL_DOWNLOADS]: The skill refers to the @rephrasy/mcp package available on the official NPM registry, which is a library provided by the skill's authoring organization for text processing.
Audit Metadata