sales-operations

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external sources (opportunities.csv, accounts.csv, and team.csv), which creates a potential surface for indirect prompt injection.\n
  • Ingestion points: Data enters the agent context via local CSV files processed by scripts and through account dictionaries in the scoring function.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential instructions embedded within the data.\n
  • Capability inventory: The skill utilizes local Python scripts for data analysis and reporting, which represent the functional capabilities exposed to the processed data.\n
  • Sanitization: No input validation or sanitization routines are defined to filter or escape content from the external files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 01:59 AM