financial-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data extracted from PDF documents, which could contain hidden instructions targeting the agent.
- Ingestion points: Text extraction from PDF documents using
pdftotextor direct file reading as described inSKILL.md. - Boundary markers: Absent. The instructions do not specify any delimiters or warnings to treat extracted text as untrusted data.
- Capability inventory: The skill performs file system writes (Markdown, HTML, and TXT files) and executes shell commands (
pdftotext) inSKILL.md. - Sanitization: No sanitization, escaping, or validation of the extracted PDF content is mentioned before it is processed or written to output files.
Audit Metadata