The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill operates purely by processing text instructions and user input through specialized agent prompts. No network operations, file system access, or credential management are present.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input during the briefing stage to generate marketing copy. Ingestion points: User responses to product, audience, and goal questions in SKILL.md. Boundary markers: None explicitly defined in the prompts to delimit user data from instructions. Capability inventory: None. The skill does not have access to shell execution, network tools, or file writing tools. Sanitization: Not present. This is the intended function of the skill and poses no risk as the agent lacks dangerous capabilities like shell access or network connectivity.

copywriter-agent