campaign-creation

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading data from local files like LIST.md and icp.md which could theoretically contain instructions intended to influence the agent. This is considered a safe and necessary part of its core functionality for managing sales campaigns.
  • Ingestion points: Reads files from .business_growth/sales/DECISIONS.md and campaign-specific LIST.md and icp.md files.
  • Boundary markers: The skill does not define specific delimiters to wrap or isolate the data being read from the files.
  • Capability inventory: Operations are limited to reading and writing local files and delegating tasks to related internal skills.
  • Sanitization: No specific content validation or escaping is applied to the ingested campaign data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 11:56 PM