campaign-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes untrusted data from external websites.
  • Ingestion points: Systematic crawling of external website pages, including homepages, case study sections, and blog posts (SKILL.md, Steps 1-4).
  • Boundary markers: The instructions lack boundary markers or explicit directives to ignore any instructions found within the researched content.
  • Capability inventory: The skill writes analyzed data to the local filesystem (profiles//campaign-strategy.md) and influences the input for subsequent campaign copywriting tasks.
  • Sanitization: No sanitization or validation of the crawled text content is implemented before the agent analyzes it to generate strategies.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 10:21 AM
Security Audit — agent-trust-hub — campaign-strategy