probability
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill presents an attack surface for Indirect Prompt Injection (Category 8) by integrating untrusted natural language input into its core decision-making logic.\n
- Ingestion points: Untrusted data enters the agent context through the
action,actor, andcontextparameters in theCALCULATEmethod, as well as thestakesparameter in theRESOLVEmethod.\n - Boundary markers: Absent. There are no delimiters or specific instructions to the LLM to ignore embedded commands within the user-provided narrative context.\n
- Capability inventory: The skill possesses the
read_filecapability to access local files (presumably character/buff data).\n - Sanitization: No evidence of input sanitization, filtering, or schema validation for the narrative parameters was found.
Audit Metadata