ai-humanizer

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external, user-provided text for humanization, which creates an indirect prompt injection attack surface.\n
  • Ingestion points: Untrusted text provided by users for analysis and rewriting, as described in SKILL.md.\n
  • Boundary markers: Absent. There are no instructions for the agent to use delimiters (like XML tags) or to ignore instructions embedded within the user text.\n
  • Capability inventory: The agent is empowered to analyze, rewrite, and present content based on the input.\n
  • Sanitization: No evidence of input validation, escaping, or filtering of the processed content was found.\n- [NO_CODE]: The skill's primary functional documentation in SKILL.md provides extensive examples for a CLI tool located at src/cli.js. However, this file is not included in the skill package, which would result in errors if the agent attempted to execute the documented commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:10 AM
Security Audit — agent-trust-hub — ai-humanizer