ClawAudit verdict

bags

testing-sagb

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

Involves real Solana financial transactions (trading, launching tokens, claiming fees) and fetches additional skill files from an external host at runtime, meaning the agent's behavior is partially defined by remotely-served content.

⚠ 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.

53
security
70
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Findings (3)

Pattern match high

Instructs covert action — may act without user awareness

heartbeat.md · code · Silently

Pattern match medium

Base64 encoding/decoding

auth.md · code · base64_encode

Pattern match low

Contains shortened/invite URL

launch.md · code · t.me/mytoken

Why the tier is capped

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

Is this flag fair?

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