copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, shell commands, or network operations. All referenced files contain static documentation related to copywriting frameworks and transitions.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions suggest reading a local file
.claude/product-marketing-context.mdfor context. This presents a theoretical ingestion point for untrusted data, but the skill lacks any capabilities to exploit such instructions. - Ingestion points:
.claude/product-marketing-context.md(referenced in SKILL.md) - Boundary markers: None specified for the content of the marketing context file.
- Capability inventory: None. The skill does not use tools for network access, file writing, or command execution.
- Sanitization: None specified.
Audit Metadata