Caveat verdict

chainstream-data

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

The skill's purchase flow instructs the agent to execute real USDC payments on Base/Solana via EIP-3009 signatures without explicit per-transaction user confirmation, presenting a risk of autonomous financial transactions.

⚠ 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.

0
security
60
transparency
70
maintenance

Findings (5)

Pattern match critical

Possible hardcoded credential

references/websocket-streams.md · code · token: 'TOKEN_ADDR

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

shared/authentication.md · code · curl -fsSL https://tempo.xyz/install | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

shared/authentication.md · code · | bash

Pattern match medium

Opens WebSocket connection

SKILL.md · frontmatter · WebSocket

Pattern match low

Popular HTTP library — network access

shared/error-handling.md · prose · downgraded · axios

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_incredential_access

Is this flag fair?

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