moai-platform-neon
Warn
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (MEDIUM): The skill is designed to ingest external content which could be manipulated to influence agent behavior.
- Ingestion points: Fetches library documentation using
mcp__context7__get-library-docs(SKILL.md). - Boundary markers: Absent; there are no instructions to the agent to treat external documentation as untrusted data.
- Capability inventory: Powerful tools including
Bash(npm:*),Bash(neonctl:*), andBash(psql:*)are enabled (SKILL.md). - Sanitization: Absent; the skill does not specify validation or filtering for documentation content before processing.
- [Command Execution] (LOW): The skill explicitly permits the use of shell commands for package management and database operations. While necessary for the skill's functionality, these tools could be abused if the agent is compromised via prompt injection.
Audit Metadata