ClawAudit verdict
crypto-scam-detector
Accesses credentials AND encodes data
Database-first scam detector using local SQLite queries for user checks with background Etherscan sync using a user-provided API key; no exfiltration behavior, appropriate for a security tool.
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.
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.
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
credential_access
Findings (4)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_key_here
References sudo — requests elevated privileges
DATABASE_ARCHITECTURE.md · code · sudo
HTTP request to bare IP address — common in malicious payloads
SECURITY.md · code · http://127.0.0.1
Python os.environ.get — reads environment variable
SECURITY.md · code · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/F). 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_accessdata_encoding Thanks — recorded.