co-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill's primary function is to provide structured frameworks for partnership identification and campaign brainstorming.
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes an attack surface for indirect prompt injection by reading project-specific context files.
- Ingestion points: The skill reads context from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md if they exist in the user's workspace.
- Boundary markers: No delimiters or instructions to ignore embedded commands within the context files are specified.
- Capability inventory: This skill does not define any tools, subprocess calls, or file-write capabilities of its own.
- Sanitization: The skill does not implement any validation or sanitization of the content found in the referenced context files.
Audit Metadata