The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it retrieves and processes external data from the web which is then used to drive workflows with significant capabilities.
Ingestion points: The skill uses WebSearch and WebFetch to gather information for mockups, and takes user-provided design ideas via $ARGUMENTS.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded in fetched web content.
Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, and Read.
Sanitization: No sanitization or validation logic is present to filter executable instructions from external content before it enters the agent's context.

gsd-sketch