copywriting
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill and its associated reference files consist solely of natural language instructions and templates. No malicious code, obfuscation, or unauthorized system access patterns were detected.
- [PROMPT_INJECTION]: The skill includes instructions to read from
.agents/product-marketing-context.md, which creates a surface for indirect prompt injection. However, since the agent's capabilities are limited to generating marketing copy, the risk is minimal. - Ingestion points:
.agents/product-marketing-context.mdand.claude/product-marketing-context.md(referenced inSKILL.md) - Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters for this content.
- Capability inventory: Text generation only; no subprocess execution, network access, or file-writing tools are utilized.
- Sanitization: Absent; there is no instruction to validate or sanitize the ingested context.
Audit Metadata