copy-editing
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured framework for copy editing without any dangerous command execution or file system modifications.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructs the agent to read local context files (
.agents/product-marketing-context.md) to align with brand voice. This is a standard practice for context-aware agents and does not involve exfiltration of sensitive data to external servers. - [REMOTE_CODE_EXECUTION]: No remote script downloads or piped command executions are present. All references, such as the
plain-english-alternatives.md, are to local files within the skill package. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied marketing copy. While this is an ingestion surface for untrusted data, the agent lacks any capabilities (like network access or shell execution) that could be exploited through malicious instructions embedded in that text.
Audit Metadata