finance-based-pricing-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and logic for interactive consultation. It does not perform any network requests, command executions, or file system operations.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted user input as it asks for financial metrics and business context in multiple stages.
- Ingestion points: User-provided text in Step 0 (Gather Context), Step 2 (Assess Impact), and Step 3 (Evaluate Current State).
- Boundary markers: The skill does not define explicit delimiters for user-provided data.
- Capability inventory: The skill has no capabilities beyond text generation (no subprocesses, no file-writing, no network access).
- Sanitization: None, as the output is restricted to natural language dialogue.
- Assessment: Because the skill lacks any privileged tools or automated actions, the risk of instruction overriding is minimal and contained to the chat interface.
Audit Metadata