finance-forecast

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill operates as a financial modeling assistant that reads from and writes to local project data files. It does not perform any network operations or execute arbitrary system commands.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external data files. Ingestion points: Reads data/cfo/latest_forecast.json, data/cfo/assumptions.json, data/cfo/actuals.json, and data/gtm/project_context.json. Boundary markers: No explicit delimiters are present. Capability inventory: Access to read/write local files. Sanitization: None specified. Despite this surface, the risk is negligible as the skill lacks high-privilege tools like shell access or internet connectivity.
  • [DATA_EXFILTRATION]: Analysis confirms that although the skill handles sensitive financial data, it does not use any tools (e.g., curl, wget) or commands capable of transmitting this information to external servers.
  • [COMMAND_EXECUTION]: The skill does not contain any shell commands, scripts, or instructions that would lead to unauthorized command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 10:41 AM
Security Audit — agent-trust-hub — finance-forecast