ad.inside/inside-ads

http:https://app.inside.ad/api/mcp

scanned 2026-08-28T07:50:50.695Z rulepack rulepack-2026.08.1 transport http tools 3

crit 1 high 0 med 2 low 0 info 0

critical remote-no-auth LLM08 deterministic

Remote server returns mutating tools without authentication

We enumerated 1 state-changing tool(s) over an unauthenticated connection. Anyone who can reach the endpoint can drive them.

at tool create_campaign_draft · field endpoint

1 mutating tools, no auth header

reproduce: mcpaudit-scan --http https://app.inside.ad/api/mcp --check remote-no-auth

medium missing-annotations LLM08 deterministic

Mutating tool ships without readOnlyHint

Tool "create_campaign_draft" looks state-changing but declares no readOnlyHint. Agents use that flag to gate risky calls; without it they cannot tell this tool apart from a safe read.

at tool create_campaign_draft · field annotations

{}

reproduce: mcpaudit-scan --http https://app.inside.ad/api/mcp --check missing-annotations

medium schema-freeform-sink LLM05 deterministic

Unvalidated free-form input on a sink-like parameter

Parameter "url" of tool "estimate_campaign" accepts a free-form string with no enum/pattern/format. If it reaches a shell, filesystem, or outbound request, it is an injection/SSRF surface.

at tool estimate_campaign · field inputSchema.properties.url

{"type":"string","description":"Product landing page URL"}

reproduce: mcpaudit-scan --http https://app.inside.ad/api/mcp --check schema-freeform-sink

This is an automated, point-in-time report from passive metadata analysis (the server's own initialize and tools/list advertisement). No tools were invoked. The grade reflects deterministic checks only; findings marked "llm" are triage signals for human review and do not affect the grade. Verify any finding with its reproduce command. Rulepack rulepack-2026.08.1.