The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires a CLI utility named raqeeb. It instructs the agent to execute commands for directory scanning (raqeeb scan .), remote content fetching (raqeeb url URL), and file system modification (raqeeb fix ., raqeeb init --write). These operations are consistent with the tool's primary purpose as a code auditor.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection. Ingestion points include the raqeeb url command (fetching untrusted external web content) and raqeeb scan (processing local code files). While these inputs are used for RTL auditing, the skill does not explicitly define boundary markers or sanitization procedures for the ingested data. The capability to write to the file system via raqeeb fix and raqeeb init is a functional capability of the tool, but the risk is minimized by the context of standard development workflows.

raqeeb