code-like-me

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The instructions guide the agent to perform standard development tasks with high precision and user oversight.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool for running project-specific verification commands such as tsc --noEmit and linters. This is expected behavior for an automated coding assistant.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its ingestion of external data. Ingestion points: Task descriptions from Jira (Atlassian MCP) and design context from Figma (Figma MCP). Boundary markers: None. Capability inventory: The agent can modify files (Edit, Write) and execute shell commands (Bash). Sanitization: None. This risk is inherent to integrations with external task trackers and is mitigated by the instruction to obtain user approval for all plans before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 01:31 PM