The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown instructions and does not contain any executable scripts, binary files, or configuration code.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external websites, which presents a surface for indirect prompt injection. \n
Ingestion points: The skill instructs the agent to fetch documentation from spec.whatwg.org, w3.org/TR/, and tc39.es. \n
Boundary markers: The instructions do not define specific delimiters to separate external content from the agent's internal prompt context. \n
Capability inventory: The skill relies on the agent's WebFetch tool to retrieve external data. \n
Sanitization: No logic is provided to sanitize or validate the content retrieved from the external URLs. \n
Note: The target domains are restricted to official, high-reputation standards organizations, which effectively mitigates the risk of malicious payload injection.

readable-spec