The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local project files and external website content during QA checks.
Ingestion points: Reads local code (Next.js, React, static files) and navigates to external URLs to verify links and accessibility.
Boundary markers: Absent; there are no instructions to the agent to treat external content strictly as data.
Capability inventory: Shell command execution (npm run build, npm run lint), file system access, and network navigation.
Sanitization: None; the skill does not specify any sanitization or filtering of the content it parses.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to build and lint the project.
Evidence: npm run build and npm run lint commands are specified in the SKILL.md file for checking project health.

website-qa