skills/luisurrutia/skills/humanize/Gen Agent Trust Hub

humanize

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill presents a vulnerability surface for indirect prompt injection. It ingests untrusted text data for processing and possesses the capability to modify files on the local system.
  • Ingestion points: The skill reads user-provided prose and text from requested file paths (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the text being humanized.
  • Capability inventory: The skill includes an edit mode that specifically instructs the agent to 'Modify the requested file in place' (SKILL.md).
  • Sanitization: There is no logic provided to sanitize, escape, or validate the content of the text before it is written back to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 09:18 PM
Security Audit — agent-trust-hub — humanize