kata-help
Fail
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: CRITICALCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command (
cat "$CLAUDE_PLUGIN_ROOT/VERSION") to populate version information at runtime. This uses shell execution for context gathering within the agent's environment.\n- [DYNAMIC_EXECUTION]: The utility scriptscripts/kata-lib.cjsperforms file system operations to manage project configuration files, including writing and updating JSON settings in the.planning/directory.\n- [INDIRECT_PROMPT_INJECTION]: The Kata framework reads and processes various project files (such asPROJECT.mdandROADMAP.md) to guide agent behavior. This creates a surface for indirect injection if these planning files are modified by untrusted content.\n- [AUTOMATED_SCAN_ALERT]: An automated reputation scanner flaggedSKILL.md(FileRepMalware [Misc]). This detection is likely a heuristic hit on the administrative command strings and framework execution triggers described in the markdown reference guide rather than a confirmed malicious payload.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata