paper-summary
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which introduces a surface for indirect prompt injection attacks.
- Ingestion points: PDF files, URL links, and pasted text content as described in SKILL.md.
- Boundary markers: The instructions do not define delimiters or specific markers to isolate the user-provided content from the agent's instructional context.
- Capability inventory: The workflow utilizes tools such as
extract_pdfs_full_contentandextract_pdfs_key_infoto ingest data. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content extracted from the external sources.
Audit Metadata