co-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill consists of instructional content for co-marketing strategy and does not include executable scripts, network operations, or sensitive data access.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential injection surface. 1. Ingestion points: The agent is instructed in SKILL.md to read local context files such as .agents/product-marketing.md. 2. Boundary markers: No specific delimiters are defined for the ingested content. 3. Capability inventory: The skill contains no shell execution, network operations, or file-writing capabilities across any scripts. 4. Sanitization: Not applicable as the skill is purely descriptive. Due to the absence of dangerous capabilities, this surface is considered safe.
Audit Metadata