The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data from user requests and local workspace files to generate functional HTML files, which represents a potential attack surface for reflected content or script injection.
Ingestion points: The instructions direct the agent to analyze user requests, project design languages, and documentation found in repository files such as AGENTS.md and CLAUDE.md (as specified in SKILL.md).
Boundary markers: The skill does not define specific delimiters or "ignore instructions" warnings to help the agent distinguish between its own system instructions and potentially adversarial content within the ingested data.
Capability inventory: The skill possesses the capability to write .html files containing inline JavaScript directly to the user's workspace (documented in the 'Build contract' section of SKILL.md).
Sanitization: There are no explicit requirements for the agent to sanitize, escape, or validate external input before interpolating it into the generated code artifacts.

effective-html