Caveat verdict
celo-agent-skills
Celo blockchain development playbook covering viem, thirdweb, Foundry, and fee abstraction; all code examples are standard blockchain development patterns matching the stated purpose with no exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Permission integrity
network_out
Findings (7)
Possible hardcoded credential
SKILL.md · code · TOKEN = "0x765DE816845861e75A25fCA122bb6898B8B1282a
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -L https://foundry.paradigm.xyz | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
HTTP request to bare IP address — common in malicious payloads
skills/evm-foundry/references/foundry-config.md · code · http://127.0.0.1
References tunneling service
skills/minipay-integration/references/testing-guide.md · code · ngrok
Accesses sensitive environment variables
skills/contract-verification/references/verification-config.md · code · process.env.PRIVATE_KEY
Opens WebSocket connection
skills/celo-rpc/references/rpc-providers.md · prose · downgraded · WebSocket
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.
network_out Is this flag fair?
Thanks — recorded.