page-cro
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill files.
- [PROMPT_INJECTION]: The skill contains instructions to ingest data from project context files (e.g.,
.agents/product-marketing-context.md) and user-provided URLs. While these represent surfaces for indirect prompt injection where external data could attempt to influence the agent's behavior, the risk is negligible as the skill lacks high-privilege capabilities such as shell access or network writing tools. - Ingestion points: Reads project-specific marketing context files and analyzes content from user-provided marketing URLs.
- Boundary markers: None explicitly defined for the external context files.
- Capability inventory: No tool usage or command execution is specified; the skill is limited to providing text-based analysis and recommendations.
- Sanitization: No specific sanitization or validation of the input content is performed.
Audit Metadata