Caveat verdict

clawhub-scanner

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

A security scanner for detecting malicious patterns in installed ClawHub skills; executionSinkDetected reflects the scan CLI commands shown as usage examples, and the skill's purpose (detecting C2 infrastructure, credential theft, prompt injection) is legitimate defensive security tooling.

⚠ 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
80
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (17)

Pattern match high

Uses eval() — can execute arbitrary code

SKILL.md · prose · downgraded · eval(

Pattern match high

Pipe to bash — executes piped content as shell commands

src/scanner.ts · prose · downgraded · |bash

Pattern match high

Pipe to sh — executes piped content as shell commands

src/scanner.ts · prose · downgraded · |sh

Pattern match high

Dynamic Function constructor — equivalent to eval()

tests/patterns.test.ts · prose · downgraded · new Function(

Pattern match high

Recursive delete from root or home — destructive command

tests/patterns.test.ts · prose · downgraded · rm -rf /

Pattern match high

Prompt injection — tries to override agent instructions

tests/scanner.test.ts · prose · downgraded · Ignore all previous instructions

Pattern match medium

Accesses system credential store

CLAUDE.md · prose · downgraded · keychain

Pattern match medium

Accesses cloud provider credentials

CLAUDE.md · prose · downgraded · ~/.aws

Pattern match medium

References child_process — can spawn system processes

src/patterns.ts · prose · downgraded · child_process

Pattern match medium

Uses exec() — may execute shell commands

src/scanner.ts · prose · downgraded · exec(

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

tests/patterns.test.ts · prose · downgraded · http://91.92.242.30

Pattern match medium

Accesses .ssh directory

tests/patterns.test.ts · prose · downgraded · .ssh/

Pattern match medium

Enumerates all environment variables

tests/patterns.test.ts · prose · downgraded · Object.keys(process.env)

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · WebSocket

Pattern match low

Popular HTTP library — network access

src/patterns.ts · prose · downgraded · axios

Pattern match low

String.fromCharCode — can build strings to evade detection

src/patterns.ts · prose · downgraded · String.fromCharCode

Pattern match low

Accesses sensitive environment variables

tests/patterns.test.ts · prose · downgraded · process.env.AWS_SECRET_ACCESS_KEY

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). 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.

package_install

Is this flag fair?

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