The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill generates configuration files and executes shell commands based on user-provided requirements. This creates a surface where the agent might inadvertently process malicious instructions embedded in user prompts or existing project data.
Ingestion points: The skill ingests user requests for specific linting configurations as described in SKILL.md and references/examples.md (e.g., "Configure ESLint for TypeScript with React").
Boundary markers: The skill lacks explicit boundary markers or instructions to isolate user-provided data from system instructions.
Capability inventory: The skill is configured to use Read, Write, Edit, and Bash tools in the allowed-tools section of SKILL.md.
Sanitization: There is no evidence of input validation or sanitization routines to ensure user-provided strings do not contain malicious command injections or prompt overrides before being used in file writes or shell executions.

windsurf-linting-config