The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by reading external artifacts such as codebases or design documents to facilitate its critique analysis.
Ingestion points: The skill uses Read, Grep, and Glob tools to ingest content from the project environment (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions that might be embedded within the artifacts being critiqued.
Capability inventory: Execution is restricted to file-reading tools (Read, Grep, Glob), which limits the impact of potential injections.
Sanitization: No explicit sanitization or filtering of external file content is described before the agent processes it.

design-critique