The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute grep commands and a Node.js script (styleseed-check.mjs) to scan project files for design system violations.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project files and configuration data, which presents a surface for indirect prompt injection attacks.
Ingestion points: The skill reads project source files (specified by $ARGUMENTS) and configuration files within the .styleseed/ directory using Read, Grep, and Glob tools.
Boundary markers: The instructions do not define any boundary markers or delimiters to help the agent distinguish between data to be linted and potential instructions embedded within that data.
Capability inventory: The skill has access to Bash (permitting execution of node and grep), Read, Grep, and Glob tools, which could be abused if the agent follows instructions found within analyzed files.
Sanitization: There is no evidence of content sanitization or instruction-filtering for the data retrieved from project files before it is processed by the agent.

ss-lint