regex-vs-llm-structured-text

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a hybrid parsing pipeline where untrusted input text (original_text) is passed directly into an LLM prompt in the validate_with_llm function. This creates a surface for indirect prompt injection, where an attacker could embed malicious instructions in the text being parsed to manipulate the LLM's validation logic.\n
  • Ingestion points: The content parameter in process_document and the original_text parameter in validate_with_llm (SKILL.md).\n
  • Boundary markers: Absent. Input text is concatenated with instructions using f-strings without delimiters (e.g., XML tags or backticks) or instructions to ignore embedded commands.\n
  • Capability inventory: The skill performs LLM invocations using the client.messages.create method with the 'claude-haiku-latest' model.\n
  • Sanitization: No escaping, sanitization, or validation of the input text is performed before it is included in the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 10:28 AM
Security Audit — agent-trust-hub — regex-vs-llm-structured-text