The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill instructs the agent to execute yarn prettier --write <file-path>. This is a benign command used for standard code/markdown formatting and aligns with the skill's primary purpose. It does not involve downloading untrusted scripts or escalation.
[Indirect Prompt Injection] (LOW): The skill exhibits an attack surface for indirect prompt injection because it is designed to read, process, and write back to external documentation files.
Ingestion points: External markdown/MDX files accessed via Read, Grep, and Glob tools.
Boundary markers: Absent; there are no specific instructions to the agent to treat content within documentation files as untrusted or to ignore embedded instructions.
Capability inventory: The skill has Write and Bash capabilities, allowing it to modify files and run local shell commands.
Sanitization: No sanitization or validation of input file content is performed before processing or formatting.

docs-write