compliance-notification-dispatcher

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external expense claim data and employee information to generate email templates, which creates a surface for indirect prompt injection.
  • Ingestion points: Processes external expense claim data and employee contact information as defined in the skill prerequisites.
  • Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands within the ingested data, which could lead to the agent following malicious instructions present in claim descriptions.
  • Capability inventory: The skill is capable of executing local scripts (scripts/analyze_claims.py), sending emails to employees and managers, and performing database operations on a Snowflake instance.
  • Sanitization: No evidence of data validation or sanitization is provided for the external data before it is interpolated into email templates or database fields.
  • [COMMAND_EXECUTION]: The skill requires the execution of a local Python script (scripts/analyze_claims.py) to identify compliance issues. While this is expected behavior for the skill's purpose, it represents a core capability that interacts with ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:26 PM
Security Audit — agent-trust-hub — compliance-notification-dispatcher