ktuner
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill instructs the agent to use
sudowhen executing thetune,fix, androllbacksubcommands of thektunerutility. This allows the agent to perform actions with root-level privileges to modify system kernel parameters. - [COMMAND_EXECUTION]: The skill relies on the
run_shell_commandtool to interact with thektunercommand-line interface, executing various subcommands to diagnose and modify the host system. - [INDIRECT_PROMPT_INJECTION]: The agent is designed to ingest JSON-formatted output from the
ktunertool and use it to generate explanations and advice for the user. This creates a potential surface where the tool's output can influence the agent's logic. - Ingestion points: The agent parses the standard output of
ktuner checkandktuner why <parameter>(SKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the tool output are provided.
- Capability inventory: The skill has access to
run_shell_commandand is explicitly authorized to usesudofor specific operations (SKILL.md). - Sanitization: No validation or sanitization steps are defined for the data returned by the shell commands before the agent processes it.
Audit Metadata