synthesizing-financial-statements
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external SEC filings (10-K, 10-Q), which are untrusted inputs that could contain hidden instructions intended to influence the agent.\n
- Ingestion points: SEC filings (10-K, 10-Q) listed in the 'Inputs To Gather' section.\n
- Boundary markers: Absent. The skill does not provide instructions to use delimiters or ignore embedded prompts within the data.\n
- Capability inventory: None. The skill does not include scripts, tool definitions, or subprocess execution patterns.\n
- Sanitization: Absent. No instructions are provided for filtering or escaping the content of the filings.
Audit Metadata