copywriting
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill attempts to read local project context files such as
.agents/product-marketing.mdor.claude/product-marketing.md. This is standard behavior for agents to gather task-specific context and does not target sensitive system or user credentials. - [INDIRECT_PROMPT_INJECTION]: The skill processes project-provided marketing context to generate copy. While this represents an ingestion surface for external data, the skill lacks dangerous capabilities—such as network operations or code execution—that could be exploited via malicious input in those files.
- [COMMAND_EXECUTION]: No shell commands, script execution patterns, or dynamic context injections (
!command) were found in the skill or its referenced files. - [EXTERNAL_DOWNLOADS]: No external network requests, remote script fetches, or dependency installations were detected.
Audit Metadata