chrome-ext-develop

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill provides shell command templates in WORKFLOW.md and REFERENCE.md that use user-provided placeholders such as '[extension-name]'. If the AI agent executes these commands (e.g., mkdir [extension-name]) without sanitizing the user input, it could lead to arbitrary command injection.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted user data which is later used to perform high-privilege shell operations. 1. Ingestion points: Extension concept, requirements, and name gathered in WORKFLOW.md Phase 1 and Phase 4. 2. Boundary markers: Absent; there are no instructions to the agent to distinguish between user data and instructions or to ignore embedded commands. 3. Capability inventory: Command execution via mkdir, npm, zip, and convert (via ImageMagick). 4. Sanitization: Absent; the skill does not provide any logic or instructions to escape or validate user-provided strings before they are utilized in shell environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM