ClawAudit verdict

vinculum

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The skill uses package installation and networking capabilities for its legitimate purpose of linking multiple Clawdbot instances.

⚠ 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.

43
security
100
transparency
100
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (7)

Pattern match medium

References agent memory files

README.md · code · MEMORY.md

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

README.md · prose · downgraded · http://192.168.1.100

Pattern match medium

References child_process — can spawn system processes

scripts/commands/relay.js · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

scripts/commands/relay.js · prose · downgraded · spawn(

Pattern match low

References tunneling service

README.md · prose · downgraded · ngrok

Pattern match low

Node http/https module — low-level network access

scripts/commands/relay.js · prose · downgraded · require('http')

Pattern match low

Opens WebSocket connection

scripts/relay-daemon.js · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 system binaries. (1 elevated: npm).

package_install

Is this flag fair?

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