Caveat verdict

clawbet

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Receives external input AND executes processes

This skill enables AI agents to make real cryptocurrency bets on a third-party platform (clawbot.bet) using Solana wallets; while the skill takes care to isolate private keys in subprocess, it facilitates real financial transactions with an external service and includes autonomous betting logic.

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

0
security
40
transparency
70
maintenance

What it does

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

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Capability combination critical

Writes files AND executes processes — may drop and execute malicious scripts

LLM05 · LLM06 · ASI05

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Capability combination high

Installs packages AND executes processes — opaque dependency chain with execution

LLM03 · ASI04

Capability combination high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · api_key="YOUR_KEY

Pattern match high

subprocess execution — runs system commands from Python

SKILL.md · code · subprocess.run(

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("POST"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · | Method | Path | Auth | Description | |--------|------|------|-------------| | **Registration & Identity** |||| | POST | /agents/register | Public | Register n

Pattern match medium

Opens WebSocket connection

SKILL.md · code · WebSocket

Pattern match medium

Python aiohttp session — async network access

SKILL.md · code · aiohttp.ClientSession

Pattern match medium

Instructs covert action — may act without user awareness

HEARTBEAT_FRAGMENT.md · prose · downgraded · silently

Pattern match low

Popular HTTP library — network access

SKILL.md · prose · downgraded · got

Pattern match low

References agent memory files

HEARTBEAT_FRAGMENT.md · prose · downgraded · MEMORY.md

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

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