copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes an ingestion point for local product context to improve the relevance of the generated copy.\n
- Ingestion points: The skill reads
.claude/product-marketing-context.mdif available (SKILL.md).\n - Boundary markers: The instructions do not define specific delimiters for the ingested context.\n
- Capability inventory: Capabilities are limited to text generation; no high-privilege tools or network operations are involved.\n
- Sanitization: The skill relies on the integrity of the local file system and does not perform manual sanitization.\n- [SAFE]: The skill consists of conversion copywriting principles and writing templates. No malicious code, obfuscation, or persistence mechanisms were detected.
Audit Metadata