the-campaign-composer

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, unauthorized data exfiltration, or dangerous command execution were detected in this skill.
  • [DATA_EXPOSURE]: The skill reads from local files .agents/product-context.md and references/email-templates.md. This is a legitimate use case for retrieving brand context and template structures. There are no indications that this data is being sent to external third parties.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from local files which could theoretically contain instructions. However, the skill's capabilities are limited to generating email copy and checklists, presenting a negligible risk.
  • Ingestion points: Reads from .agents/product-context.md and references/email-templates.md.
  • Boundary markers: None explicitly defined for file input, though instructions are scoped to campaign generation.
  • Capability inventory: None; the skill generates text output and does not execute code, perform network requests, or modify the filesystem beyond generating its response.
  • Sanitization: Standard LLM processing of text templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:19 PM