time-timezone-convert

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). The repository instructs users to fetch and execute a remote script (https://fittings.sh/skill/call.mjs) from an unverified domain — downloading and running remote code is a high-risk vector for malware distribution.

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

  • Third-party content exposure detected (low risk: 0.10). call.mjs lets the user choose and fetch service catalog entries and any response text from fittings.sh endpoints (e.g., --search queries /catalog/search and --describe fetches /catalog/{id}), but it does not ingest arbitrary outsider-authored free text without an explicit selection path via these CLI parameters; runtime ingestion is limited to provider-generated JSON and user-supplied query strings used only to call fittings.sh, not to automatically consume external feed content.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill documentation instructs fetching and (implicitly) running remote executable code via "curl -sO https://fittings.sh/skill/call.mjs", which is a runtime fetch of code the client may execute.

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

  • Direct money access detected (high risk: 1.00). This skill explicitly describes a paid API flow that requires signing an authorization with a private key and spending USDC on the Base chain. It instructs setting FITTINGS_PRIVATE_KEY, shows example commands that perform payment, mentions a 402 signed-quote flow, and references EVM/evm-related client libraries (@x402/evm). These are specific crypto payment/wallet instructions (signing transactions/authorizations), so the skill grants direct financial execution capability.

Issues (4)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 18, 2026, 05:21 AM
Issues
4