argent-tv-interact

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection as it ingests untrusted text data (element labels and accessibility hints) from external application UIs using the describe tool.
  • Ingestion points: UI element labels and focusable element descriptions retrieved in SKILL.md.
  • Boundary markers: None identified in the instruction set.
  • Capability inventory: UI navigation, keyboard input emulation, application installation/reinstallation, and device booting.
  • Sanitization: No sanitization or filtering mechanisms for the ingested UI content are specified.
  • [COMMAND_EXECUTION]: The skill uses established command-line tools to interact with TV devices, including adb for Android TV, xcrun simctl for Apple TV simulators, and the vega and vsm CLIs for Fire TV Virtual Video Devices.
  • [EXTERNAL_DOWNLOADS]: References the amazon-devices-buildertools-mcp suite for specialized tasks such as performance trace analysis and crash symbolication on Fire TV platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 06:47 PM
Security Audit — agent-trust-hub — argent-tv-interact