ClawAudit verdict

runbox

45
🟠 Risky
Significant concerns — only install if you understand the risks

Accesses credentials AND makes external network calls

Skill requires a STELLAR_SECRET_KEY to autonomously pay 0.01 USDC per execution to a hardcoded IP address (46.101.74.170:4001) with no origin verification, then executes arbitrary code in a remote Docker container — the combination of autonomous financial transactions using a private key and remote code execution at a bare IP is genuinely elevated risk.

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.

0
security
40
transparency
90
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 makes external network calls — potential credential theft

LLM02 · 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 (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · Secret:',k.secret)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

README.md · code · http://46.101.74.170

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · | Bash

Pattern match high

Pipe to python — executes piped content as Python code

SKILL.md · prose · downgraded · | Python

Pattern match low

Python os.environ.get — reads environment variable

run.py · prose · downgraded · os.environ.get(

Pattern match low

Base64 encoding/decoding

run.py · prose · downgraded · base64-encode

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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.

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