content-humanizer
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided content ('the draft to humanize'), which establishes an indirect prompt injection surface.
- Ingestion points: Draft content is provided by the user and processed by the agent in SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the user-provided text.
- Capability inventory: The skill includes a local Python script, scripts/humanizer_scorer.py, for text analysis. However, it does not request network access, file writing permissions, or other elevated privileges.
- Sanitization: There are no documented sanitization or filtering procedures for the ingested content before analysis.
Audit Metadata