deckmate

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides Python and shell script templates designed to execute terminal commands and launch applications (e.g., /usr/bin/claude, /usr/bin/wt) via Stream Deck hotkeys.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process 'Integration Definition' JSON files to generate functional Stream Deck profiles.
  • Ingestion points: Reads blueprint configurations from the profiles/ directory (SKILL.md).
  • Boundary markers: None; the skill does not implement delimiters or specific instructions to ignore malicious directives embedded within the JSON blueprints.
  • Capability inventory: Includes a Python helper using the zipfile and os modules to write files to the system; provides instructions for shell script generation and execution (SKILL.md).
  • Sanitization: No validation or escaping mechanisms are described for the content of the processed blueprints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:49 AM