regex-vs-llm-structured-text

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a hybrid pipeline that ingests untrusted text and interpolates it into an LLM prompt, creating a surface for indirect prompt injection. \n
  • Ingestion points: The process_document function in SKILL.md accepts raw string content from potentially untrusted sources (e.g., uploaded documents or forms).\n
  • Boundary markers: The prompt template in the validate_with_llm function lacks explicit delimiters (such as XML tags or triple backticks) to isolate the untrusted original_text from the agent's instructions.\n
  • Capability inventory: No high-risk capabilities, such as shell command execution (subprocess), file system writes, or arbitrary network exfiltration, were detected in the skill's code snippets.\n
  • Sanitization: The implementation does not include logic to sanitize or escape the input text before it is processed by the LLM validator.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — regex-vs-llm-structured-text