dev-server
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the agent regarding process management and operational safety.
- [COMMAND_EXECUTION]: The skill discusses managing development processes (e.g.,
pnpm dev). These are guidelines for how the agent should use its existing tools responsibly, such as avoiding port collisions and ensuring proper cleanup of started processes. There are no hardcoded malicious commands or automated execution of untrusted scripts. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read
AGENTS.mdto identify port configurations. - Ingestion points:
AGENTS.md(runtime read). - Boundary markers: Absent.
- Capability inventory: The agent is instructed on starting/killing background processes based on this data.
- Sanitization: None mentioned.
- Note: This identifies a data ingestion surface which is standard for configuration management and presents no immediate risk in this context.
Audit Metadata