copy-editing
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied marketing copy and local brand context files, creating a vulnerability surface where instructions hidden in the data could influence the agent's behavior.
- Ingestion points: Marketing copy provided by the user for review and local context files (
.agents/product-marketing-context.mdor.claude/product-marketing-context.md). - Boundary markers: The instructions do not specify any delimiters or safety warnings to prevent the agent from following instructions embedded within the processed copy.
- Capability inventory: The skill is limited to providing text analysis and editing recommendations. It lacks tools for network communication, arbitrary shell command execution, or sensitive file system access.
- Sanitization: The skill does not implement any filtering or escaping mechanisms for the text it processes.
Audit Metadata