copywriting

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No signs of prompt injection, malicious code, or unauthorized network operations were detected in the skill instructions or reference materials.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a design that reads external context files, which represents an entry point for untrusted data.
  • Ingestion points: Reads from .agents/product-marketing-context.md or .claude/product-marketing-context.md as specified in SKILL.md.
  • Boundary markers: None identified in the prompt logic for the ingested file content.
  • Capability inventory: No high-risk capabilities such as network exfiltration, file system writes, or subprocess execution are present in the skill.
  • Sanitization: The skill does not implement specific sanitization for the data read from context files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — copywriting