skills/openaec-foundation/erpnext_anthropic_claude_development_skill_package/frappe-agent-debugger/Gen Agent Trust Hub
frappe-agent-debugger
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
benchCLI commands for site administration, database inspection, and log monitoring.\n- [REMOTE_CODE_EXECUTION]: Includes documentation for remote debugging attachment withdebugpyand dependency management usingbench pip install.\n- [PROMPT_INJECTION]: Identified an indirect prompt injection surface when the agent processes logs or tracebacks. \n - Ingestion points: Application logs, system logs, and Error Log DocType entries.\n
- Boundary markers: No explicit delimiters used for external data.\n
- Capability inventory: Ability to run shell commands, perform SQL queries, and read system files.\n
- Sanitization: Standard SQL parameterization is recommended, but no content sanitization for processed log entries is provided.
Audit Metadata