skills/5dive-ai/skills/copywriting/Gen Agent Trust Hub

copywriting

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and reference files focus entirely on copywriting principles and templates. There is no evidence of malicious code, obfuscation, or persistence mechanisms.
  • [DATA_EXPOSURE]: The skill attempts to read local product marketing context files (e.g., .agents/product-marketing.md) to inform its output. This is a legitimate use of project-specific context and does not target sensitive system or credential files.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from local marketing context files, creating a surface for potential indirect prompt injection. However, this is a standard design for context-aware skills and the risk is mitigated by the skill's lack of dangerous capabilities beyond text generation.
  • Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, product-marketing-context.md (referenced in SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: None (limited to text generation)
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 06:48 AM
Security Audit — agent-trust-hub — copywriting