plugin-runtime-debug
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as user-visible strings, browser console output, and host source code, which could potentially contain malicious instructions.\n
- Ingestion points: Capturing exact user-visible strings and console output during reproduction steps (SKILL.md).\n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the analyzed logs or code.\n
- Capability inventory: The skill suggests using shell commands for process management and environment inspection (e.g.,
taskkill,Get-Item).\n - Sanitization: No sanitization or validation processes are described for handling the captured strings or logs before they are processed by the agent.\n- [COMMAND_EXECUTION]: The instructions recommend using various shell commands to manage the local development environment, including
taskkill /PID <pid> /T /Fto terminate process trees on Windows andGet-Itemto verify directory link types. These commands are contextually appropriate for resolving common development issues such as port binding conflicts and installation mode verification.
Audit Metadata