ClawAudit verdict

torch-prediction-market-bot

torchpredictionmarketkit

🟠 Risky

Significant concerns — only install if you understand the risks

Accesses credentials AND encodes data

The skill provides autonomous vault-based prediction market bot for Torch Market on Solana, but the use of multiple capabilities raises concerns.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

transparency

maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match high

Uses eval() — can execute arbitrary code

audit.md · prose · downgraded · eval(

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match low

Accesses sensitive environment variables

lib/kit/config.js · prose · downgraded · process.env.SOLANA_PRIVATE_KEY

Permissions & capabilities

Requires 3 environment variables. (1 sensitive: name: SOLANA_PRIVATE_KEY).

package_installcredential_accessdata_encoding

I installed anyway

Check another skill Browse the registry Auditing your own skills or configs? Use the API