doc-html-to-markdown

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: 0.70). The site hosts and explicitly instructs users to curl and run a remote script (https://fittings.sh/skill/call.mjs), which is effectively downloading and executing code from the network — a common malware distribution vector even if the service itself appears legitimate; the other URLs are API endpoints and are lower risk.

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

  • Third-party content exposure detected (medium risk: 0.30). The skill endpoint POSTs user-supplied html (request body) to https://fittings.sh/v1/doc/html-to-markdown, so outsider-provided free text is ingested into the runtime for processing.

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

  • Direct money access detected (high risk: 1.00). The skill explicitly includes on-chain/crypto payment behavior: it returns a 402 with a signed quote, requires the client to sign an authorization with a private key (FITTINGS_PRIVATE_KEY), and describes settling in USDC on Base with a facilitator. It even references @x402/evm and shows example commands exporting a private key and performing a paid call. These are specific crypto payment primitives (wallet signing and settlement), so the skill 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