skills/homeassistant-ai/ha-mcp/wt/Gen Agent Trust Hub

wt

Warn

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell script uses the $ARGUMENTS variable directly within multiple commands, such as git worktree add worktree/"$ARGUMENTS". While double quotes prevent word splitting, Bash still evaluates command substitutions (e.g., $(...)) and backticks inside them. This allows an attacker to execute arbitrary shell commands by crafting a malicious branch name.\n- [PROMPT_INJECTION]: The skill ingests untrusted data through the $ARGUMENTS parameter and uses it in a sensitive execution context (shell) without validation.\n
  • Ingestion points: $ARGUMENTS parameter used in SKILL.md shell block.\n
  • Boundary markers: None present.\n
  • Capability inventory: Execution of arbitrary Bash commands, file system access, and network-enabled Git operations.\n
  • Sanitization: None; the raw argument is directly interpolated into the shell command string.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 23, 2026, 03:51 PM
Security Audit — agent-trust-hub — wt