dnd
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for browser automation (
playwright-cli), video processing (ffmpeg), and system utility tasks (kill-port,mkdir,cp). These are standard operations for the skill's intended purpose of coordinate-based QA. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by reading external data from web pages under test. An attacker-controlled page could theoretically inject malicious instructions into the browser console or UI elements.
- Ingestion points: Browser UI snapshots, console error logs, and network request data captured via
playwright-cli(SKILL.md). - Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings for processing the captured browser output.
- Capability inventory: The skill uses
playwright-clito interact with browsers and evaluate JavaScript,ffmpegfor media processing, and general shell access for file management (SKILL.md). - Sanitization: There is no specified logic for sanitizing or validating UI text or console logs before they are processed by the agent.
Audit Metadata