ai-rewriting-text

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection where untrusted text is processed by the AI.
  • Ingestion points: Untrusted text enters via the source_text field in various DSPy signatures (e.g., RewriteText in SKILL.md).
  • Boundary markers: No explicit delimiters are used to separate user input from system instructions.
  • Capability inventory: The skill is limited to LLM text generation; no subprocess or file system operations were detected.
  • Sanitization: No input validation or escaping is applied to the source text before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 06:45 PM
Security Audit — agent-trust-hub — ai-rewriting-text