The Agent Skills Directory

[PROMPT_INJECTION]: Automated detectors identified potential concealment patterns; however, these represent legitimate instructions for task routing and agent efficiency, ensuring the agent remains within the defined library scope. No attempts to bypass safety filters or override core agent behavior were found.
[COMMAND_EXECUTION]: The skill utilizes standard local diagnostic and build tools such as pkg-config, ls, cat, and doca_caps. These commands are consistent with the intended purpose of assisting in development and debugging on a DOCA-enabled host.
[PRIVILEGE_ESCALATION]: The instructions explicitly discourage the use of sudo and provide guidance on resolving permission issues through path and configuration adjustments, adhering to the principle of least privilege.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided application code and error logs, which is a standard attack surface for development tools. The instructions mitigate this by guiding the agent to perform incremental, human-in-the-loop modifications and verify system state rather than executing arbitrary generated code.

doca-telemetry-exporter