x-presence

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs making a POST that includes user credentials (username/password/totp_secret) in the request body, which requires the LLM/agent to accept and embed secrets verbatim into generated requests — a direct secret-handling/exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The GitHub and vendor docs look benign, but the cluster of twitr.sh endpoints (a non-official, Twitter-imitating domain used for account connect/post APIs and docs) is a high-risk/typosquatting third-party service that could be used for credential harvesting or distributing malicious binaries.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow reads outsider-authored free text from X via GET https://twitr.sh/api/monitors/{id}/events... in “The cycle” step 1 (“Read new events”), which are then analyzed/used for reply drafting.

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

• Direct money access detected (high risk: 1.00). The skill explicitly requires and uses the user's crypto wallet to pay for API actions: it states "Every call is paid per request from the user's wallet" and lists per-call costs, instructs to confirm wallet presence (x402 / AgentCash MCP), shows wallet-signed account connection, and documents creating prepaid monitors and write calls that charge the wallet (including guidance on which chains to pay on). These are concrete, wallet-backed payment operations (crypto/blockchain payments) and API endpoints that trigger paid transactions — i.e., direct financial execution capability.