The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run npm test to verify the website's status after the tagline is integrated. This is a standard development procedure and presents no security risk.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from POSITIONING.md, STORY.md, and direct user feedback to generate tagline candidates. The skill mitigates risks by applying strict formatting constraints (word and character limits), following specific purpose-driven rules, and requiring final human approval for all changes.
[DYNAMIC_EXECUTION]: The tagline.spec.ts template utilizes Playwright's page.evaluate() to decode HTML entities within a controlled browser environment for testing assertions. This is a routine and safe practice for automated UI testing.
[EXTERNAL_DOWNLOADS]: The instructions suggest a courtesy web search to verify the uniqueness of the chosen tagline. This is a functional task intended to assist the user and does not involve the retrieval or execution of remote payloads.

website-tagline