ClawAudit verdict
bitagent-skill
openclaw-bitagent
The skill appears to be a legitimate tool for interacting with BitAgent bonding curves via CLI.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (4)
Possible hardcoded credential
scripts/index.ts · prose · downgraded · token: '0x7e624D1b87ecb3985E94dbE3Db184594e4E5DB37
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Popular HTTP library — network access
package-lock.json · prose · downgraded · axios
Accesses sensitive environment variables
scripts/index.ts · prose · downgraded · process.env.PRIVATE_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.