regex-vs-llm-structured-text
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern where untrusted input text is interpolated directly into an LLM prompt for validation, which is a classic indirect prompt injection surface.
- Ingestion points: Untrusted data enters the context via the
contentparameter in theprocess_documentfunction and is passed asoriginal_texttovalidate_with_llm. - Boundary markers: The prompt template
f"Text: {original_text}\n\n..."lacks isolation markers (like XML tags or clear delimiters) or instructions to ignore potential commands embedded within the text. - Capability inventory: The code snippets demonstrate LLM invocation using an SDK client; no subprocess calls, file writing, or network operations are present.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the input text before it is interpolated into the prompt.
Audit Metadata