The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/main.cjs uses child_process.spawn to execute a JavaScript file from a computed path within the repository.
Evidence: The script at scripts/main.cjs (lines 65-69) invokes spawn(process.execPath, [securityLintPath, ...args], ...) where securityLintPath points to .claude/tools/cli/security-lint.cjs. This file is not included in the provided skill bundle, rendering its behavior unverifiable.
[PROMPT_INJECTION]: The skill processes untrusted source code from the user's environment, presenting an indirect prompt injection surface.
Ingestion points: The skill's documented process and code examples in SKILL.md utilize fs.readFileSync and ast.parse to ingest and process the content of external files.
Boundary markers: No delimiters or safety instructions are defined to prevent the agent from obeying instructions embedded within the analyzed code files.
Capability inventory: The skill possesses extensive capabilities, including Read, Grep, Bash, and Glob tools, as well as the ability to spawn subprocesses.
Sanitization: There is no evidence of input validation or sanitization of the code content before it is processed by the AST parsers.

code-style-validator