Skills
Navigate
skills/devenkhatri/everything-claude-code/regex-vs-llm-structured-text/Gen Agent Trust Hub

regex-vs-llm-structured-text

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection in the LLM validation logic.\n
  • Ingestion points: Untrusted data is processed through the content and original_text parameters in the process_document and validate_with_llm functions (SKILL.md).\n
  • Boundary markers: The prompt used in validate_with_llm lacks boundary markers (such as XML tags or triple backticks) to isolate the untrusted original_text from the instructions.\n
  • Capability inventory: The skill includes the capability to send data to an external LLM via the client.messages.create method (SKILL.md).\n
  • Sanitization: No input sanitization or filtering is applied to the source text before it is interpolated into the prompt string.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — regex-vs-llm-structured-text