tiktok-scraper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored TikTok post/comment text is ingested by calling tiktok.fetcher.sh endpoints that return content (e.g., keyword search, post comments/replies) under the required runtime workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill declares and expects runtime fetching of machine-readable resources (https://tiktok.fetcher.sh/mcp, https://tiktok.fetcher.sh/openapi.json, https://tiktok.fetcher.sh/llms.txt, https://tiktok.fetcher.sh/skill.md) which expose MCP tools and live schemas that an MCP-connected agent can fetch at runtime to change available tools/behavior, so these URLs can directly control agent prompts/operation.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly includes payment-related endpoints and crypto payment mechanics: it documents "x402 pay-per-call" accepting USDC on Base/Polygon/Arbitrum/Monad/Solana, references @x402/fetch which "signs and retries automatically", and exposes a topup/credits endpoint (POST /api/credits/topup and MCP action topup_credits). These are specific crypto payment/signing capabilities (not mere generic HTTP or browser automation), which meet the criteria for Direct Financial Execution Authority.