copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external project context files, specifically
.agents/product-marketing-context.mdor.claude/product-marketing-context.md, to gather background information before generating copy. This represents an ingestion point for untrusted data that could be manipulated to include malicious instructions. - Ingestion points: Instructions in
SKILL.mddirect the agent to read.agents/product-marketing-context.mdor.claude/product-marketing-context.md. - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore potentially malicious content within these context files.
- Capability inventory: The skill consists entirely of markdown instructions and reference files, containing no scripts, subprocess calls, or direct tool execution capabilities.
- Sanitization: There are no instructions for sanitizing or validating the content retrieved from the context files.
Audit Metadata