regex-vs-llm-structured-text

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection in the validate_with_llm function.
  • Ingestion points: The content parameter in the process_document function (SKILL.md) is the primary entry point for untrusted data.
  • Boundary markers: Absent. The LLM prompt in validate_with_llm interpolates the original_text directly using only basic text labels, which may allow embedded instructions to influence the model's behavior.
  • Capability inventory: The skill does not possess high-risk capabilities such as file system access, arbitrary command execution, or network requests beyond the intended LLM call.
  • Sanitization: Absent. There is no evidence of input validation, escaping, or structural filtering of the processed text before it is interpolated into the LLM prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:39 AM