The Agent Skills Directory

[Prompt Injection] (HIGH): High risk of Indirect Prompt Injection. The skill is configured to read and process external requirement documents (PBIs) to generate design specifications.
Ingestion points: Untrusted data enters the agent context through the Read tool when processing {pbi-file} via the /design-spec command.
Boundary markers: Absent. The skill does not use delimiters or provide instructions to the agent to ignore potentially malicious embedded instructions in the source requirements.
Capability inventory: The skill has powerful tools including Write, Edit, and WebSearch, which could be abused if the agent follows instructions hidden within a requirement file.
Sanitization: No sanitization, escaping, or validation of the external content is specified before the data is interpolated into the workflow.

ux-designer