add-a-store
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill instructions promote security best practices, specifically instructing the agent to keep connection strings redacted and avoid exposing credentials in port or failure messages.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development commands (
pnpm turbo run check test build) to verify implementation. These are routine operations within a development environment and do not involve unauthorized privilege escalation or persistence. - [INDIRECT_PROMPT_INJECTION]: The skill involves reading local files (e.g.,
AGENTS.md,packages/database/src/model.ts) to inform its actions. While this represents an ingestion surface for untrusted data if those files were compromised, the instructions explicitly command the agent to implement strict schema validation and decoding (PersistedRunLogRowSchema) to mitigate risks from malformed or malicious data.
Audit Metadata