troubleshoot-app
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to read sensitive configuration files including ".env*" and deployment metadata to identify project dependencies. Accessing environment files exposes infrastructure details that are typically restricted.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from live web pages via browser interactions, GitHub issue descriptions, and log entries. Ingestion points include the accessibility tree, error messages, and issue bodies. The agent has significant capabilities including file system modification and command execution. The instructions do not define explicit boundary markers or sanitization procedures to isolate this untrusted content from the agent's operational logic.
- [COMMAND_EXECUTION]: The workflow involves executing shell-based CLI tools such as "pnpm exec convex" to query live application data. This provides a mechanism for command execution within the agent's environment.
Audit Metadata