plan-design

Warn

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl within a bash script to interact with the OpenAI Images API. Variables like $PROMPT_A, $PROMPT_B, and [surface-slug] are interpolated directly into shell commands. If these values contain shell metacharacters (e.g., through a maliciously crafted Linear issue title or surface name), it could lead to arbitrary command execution on the host machine.
  • [EXTERNAL_DOWNLOADS]: The skill downloads image assets from OpenAI's API (api.openai.com) and saves them locally using base64 -d. While OpenAI is a well-known service, the skill retrieves this data over the network and executes a decoding utility on the output.
  • [REMOTE_CODE_EXECUTION]: The skill uses a Task tool to spawn a subagent that generates HTML/CSS files. While the subagent itself is part of the agent's internal capabilities, the generated HTML is written to the local filesystem and subsequently uploaded to Linear, creating a path where generated code is stored and distributed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 25, 2026, 02:27 PM
Security Audit — agent-trust-hub — plan-design