superagent-cli

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the superagent CLI to start the editor environment, manage worktrees, and control interactive terminal sessions.
  • [DYNAMIC_EXECUTION]: Provides functionality to evaluate arbitrary JavaScript in browser contexts and dispatch commands to shell terminals, which are core features for the intended automation use-case.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: Facilitates access to browser cookies, terminal output history, and page screenshots.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface by processing potentially untrusted data from external sources. 1. Ingestion points: Browser accessibility tree snapshots and terminal output buffers. 2. Boundary markers: No explicit delimiters or ignore-instructions are used when processing external data. 3. Capability inventory: Ability to execute shell commands, perform file uploads to browser inputs, and evaluate JavaScript. 4. Sanitization: No specific filtering or validation of ingested content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 07:11 PM
Security Audit — agent-trust-hub — superagent-cli