marketing-cold-email
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to automatically read project-specific marketing files (e.g.,
.agents/product-marketing.mdor.claude/product-marketing.md) before generating content. This behavior creates a surface for indirect prompt injection, as malicious instructions embedded in these documentation files could attempt to subvert the agent's behavior or override its writing guidelines. - Ingestion points: The agent reads content from
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdfiles located in the project root. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to treat the ingested marketing content as untrusted data.
- Capability inventory: The skill's capabilities are primarily restricted to text generation. It does not include tools or instructions for executing code, writing to the file system, or performing network operations.
- Sanitization: No sanitization or validation logic is present to filter potentially malicious instructions from the ingested context files.
Audit Metadata