deficiency-statement-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The
html_contentfield inSKILL.mdused for processing raw inspection reports. - Boundary markers: Absent; there are no explicit instructions or delimiters used to separate user-provided content from the agent's instructions.
- Capability inventory: The skill utilizes regex and string manipulation for data extraction; it does not require or use high-risk capabilities such as network access, file system writes, or dynamic code execution.
- Sanitization: Basic sanitization is performed via regular expressions (
re.sub) to remove HTML tags from the extracted text.
Audit Metadata