nara
Fail
Audited by Snyk on Mar 13, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt includes explicit CLI options to import mnemonics/private keys (e.g.,
wallet import [-m <mnemonic>] [-k/--private-key <key>]) and shows commands where a user would supply secret values verbatim on the command line, which forces inclusion of secrets in commands/outputs and poses a high exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches quest content from remote RPC/relay endpoints (see "Step 3: Fetch: npx naracli quest get --json" and the --rpc-url/--relay options) and the workflow requires the agent to read and "Analyze the question and compute the answer" (Step 5), meaning untrusted public quest data or content from arbitrary URLs can directly influence agent decisions and subsequent tool use.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx naracli which at runtime downloads and executes the naracli package from the npm registry (see https://www.npmjs.com/package/naracli), so an external URL is used to fetch and execute remote code that the CLI depends on.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly a blockchain CLI for the NARA token and includes multiple commands that move value and manage wallets: e.g., wallet create/import, transfer , transfer-token, quest stake/unstake, zkid deposit/withdraw, agent register (costs NARA), sign [--send] (signs and broadcasts transactions), and options to point at RPC/relay endpoints. These are specific crypto/transaction operations (wallet management, signing, broadcasting, token transfers and staking), not generic tooling. Therefore it provides direct financial execution capability.
Issues (4)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata