The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts, specifically scripts/file_stats.py and scripts/dependency_mapper.py, using the Bash tool to automate code analysis. This is a standard functional pattern for architectural tools, but it involves subprocess spawning.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes untrusted source code from the project directory using Read, Grep, and Glob. There is a potential risk that malicious instructions embedded in the code being analyzed (e.g., in comments or string literals) could attempt to influence the agent's findings or behavior.
Ingestion points: Project source code files accessed via Read, Grep, and Glob tools.
Boundary markers: Not explicitly defined in the provided instructions; the agent is directed to scan and flag findings based on pattern matching.
Capability inventory: The agent has access to Bash, Read, Grep, and Glob tools, enabling file system access and script execution.
Sanitization: No explicit sanitization or filtering of the ingested code content is mentioned before it is processed by the agent.

rc-codeprobe-architecture