marketing-co-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and strategic frameworks. No malicious patterns, obfuscation, or remote code execution vectors were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include reading from local context files such as
.agents/product-marketing.md. While this represents a data ingestion surface where external content could influence the agent, the skill lacks any high-risk capabilities (like command execution or network exfiltration) that would make this an exploitable vulnerability. The instructions encourage human-in-the-loop validation of generated ideas.
Audit Metadata