The Agent Skills Directory

[SAFE]: No malicious patterns, suspicious command execution, or credential theft attempts were identified. The skill's behavior is consistent with its stated purpose of design system linting.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content by reading local files specified by the user. This creates a surface for indirect prompt injection where an attacker could place malicious instructions in code comments. However, the risk is minimized by the skill's reliance on specific regex-based grep patterns and a rigid output structure.
Ingestion points: Local files and directories provided through the $ARGUMENTS variable (SKILL.md).
Boundary markers: Absent; there are no explicit delimiters used when reading file contents to distinguish data from instructions.
Capability inventory: Read, Grep, Glob, Bash (SKILL.md frontmatter).
Sanitization: Absent; the file contents are processed directly via regex without escaping or validation.

ss-lint