starchild-dao

Warn

Audited by Snyk on Jul 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s “List proposals” workflow fetches free-form title/detail from the public API GET https://token.starchild.software/api/proposals, and those untrusted outsider-authored strings are ingested into the agent context for display/confirmation.

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

  • Direct money access detected (high risk: 1.00). This skill specifically integrates with a crypto token and wallet: it references the $STARCHILD ERC‑20 contract (address given) and requires reading balanceOf, constructs EIP‑712 typed data, and performs wallet signatures for Vote and Proposal messages (with nonce/deadline) which are POSTed to the governance API. Those are explicit crypto/blockchain signing capabilities (wallet-bound, on‑record governance actions) rather than generic I/O. Even though votes/proposals are gasless and do not transfer tokens, the skill is explicitly designed to use wallet signatures and interact with token-weighted governance — which falls under "Crypto/Blockchain (Wallets, Swaps, Signing)" in the policy.

Issues (2)

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
MEDIUM
Analyzed
Jul 5, 2026, 02:12 PM
Issues
2
Security Audit — snyk — starchild-dao