cold-email

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed exclusively of Markdown documentation and instructions. There is no executable code (Python, JavaScript, or shell scripts) included in the package.
  • [SAFE]: No network operations (such as curl or wget) or external data exfiltration patterns were identified.
  • [SAFE]: The skill does not request or use any high-risk tools or permissions. It primarily focuses on text generation based on provided copywriting frameworks.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an ingestion surface for external data.
  • Ingestion points: The skill instructs the agent to read .agents/product-marketing-context.md or .claude/product-marketing-context.md (SKILL.md).
  • Boundary markers: None present; the agent is directed to adopt the context without specific delimiters.
  • Capability inventory: No dangerous capabilities are present in the skill (no file system writes, no network access, no subprocess execution across any files).
  • Sanitization: No validation or sanitization is performed on the ingested context. However, because the skill lacks executable tools, the risk of this surface being exploited for anything beyond text-based influence is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 11:22 PM
Security Audit — agent-trust-hub — cold-email