campaign-status

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/campaign-tracker.py, scripts/execution-tracker.py, and scripts/approval-manager.py) to process campaign registries, retrieval logs, and approval queues.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting data from external advertising and marketing platforms.
  • Ingestion points: Retrieves campaign names, descriptions, and engagement metrics from external sources including Google Ads, Meta, LinkedIn, and Mailchimp via integrated tools.
  • Boundary markers: The instructions do not define delimiters or specific markers to isolate the external content from the agent's core instruction context.
  • Capability inventory: The skill accesses application configuration files in the user's home directory and executes internal Python scripts.
  • Sanitization: There is no mention of sanitization or validation of text content retrieved from the external marketing platform APIs before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — campaign-status