Skills
Navigate
skills/craftos-dev/craftbot/humanize-ai-text/Gen Agent Trust Hub

humanize-ai-text

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external text files which could contain malicious instructions designed to influence the agent's behavior during processing.\n
  • Ingestion points: The scripts scripts/detect.py, scripts/transform.py, and scripts/compare.py read content from user-provided file paths or standard input.\n
  • Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from following commands embedded within the input text.\n
  • Capability inventory: The skill has file writing capabilities (via the -o flag in scripts and the Write tool) but does not have network access or arbitrary code execution capabilities.\n
  • Sanitization: Input text is processed using regular expression replacements for pattern matching, but no sanitization is performed to strip or neutralize potential prompt injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 01:45 AM