The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as code and design features to perform quality assurance checks.
Ingestion points: The skill ingests user-supplied content for a [complete feature or page] and loads external design principles from $frontend-design and $setup skills.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the untrusted user content from the agent's operational instructions.
Capability inventory: The agent is instructed to modify files, specifically to 'Remove console logs', 'Remove commented code', and 'Remove unused imports', which could be exploited if malicious instructions are embedded in the code being reviewed.
Sanitization: There is no evidence of content sanitization or validation logic to filter out potential prompt injection attempts within the reviewed material.
[NO_CODE]: The skill consists exclusively of markdown instructions and does not include any accompanying scripts or executable files.

polish