The Agent Skills Directory

[PROMPT_INJECTION]: Indirect prompt injection surface detected because the skill reads and processes external source code.
Ingestion points: Source code files are read from user-specified directories in scripts/quality_checker.js via fs.readFileSync.
Boundary markers: The skill does not implement delimiters or specific instructions to the agent to ignore potentially malicious commands embedded in comments within the scanned files.
Capability inventory: The skill utilizes Bash, Read, and Glob tools, which could be misused if the agent is manipulated by injected content.
Sanitization: No validation or sanitization is performed on the file content before analysis.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute its analysis script (scripts/quality_checker.js) via Node.js. This is an intended behavior for its primary function.

verify-quality