agent-swarm

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

2/2 tools missing one or more hints — ping (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); whoami (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

1/2 tool handlers declare input schemas (50%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 0/2 tool handlers wrap calls in try/catch (0%)

Wrap each tool handler body in try/catch and return a structured error response.

Tool test coverage

1/2 tools referenced in tests (50%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

14 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

8 secret values sent to console.log

Redact or omit secret values from log output.

Production dependencies are patched

0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

1/42 production deps stale: @inkjs/ui@2024-05-22 (2.2y)

Domain consistency

npm scope @agent-swarm doesn't match GitHub owner desplega-ai

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.