cfr-section-text

Fail

Audited by Snyk on Aug 18, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). One of the listed URLs points to an executable JavaScript client (https://fittings.sh/skill/call.mjs) that the documentation advises downloading and running directly, which is a high-risk distribution pattern even if the service itself appears legitimate.

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

  • Third-party content exposure detected (low risk: 0.10). The runtime workflow in call.mjs only fetches trusted first-party fittings.sh service catalog metadata and then calls a specific endpoint chosen by the user-provided service-id, so it does not ingest arbitrary outsider-authored free text without the client selecting a specific item.

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

  • Direct money access detected (high risk: 1.00). The skill explicitly describes a payment flow: the endpoint can return a "402 Payment Required" signed quote that the client must sign, and the example shows exporting FITTINGS_PRIVATE_KEY and running node call.mjs to authorize payment. It references using a wallet holding USDC on Base, a max-price cap, and packages like @x402/evm for signing. These are specific crypto/payment signing instructions (directly enabling spending), not generic tooling, so this grants direct financial execution capability.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 18, 2026, 05:16 AM
Issues
3