ClawAudit verdict

safehub

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

A security scanner for OpenClaw skills that uses Semgrep static analysis and optional Docker sandboxing to produce trust scores; all operations are local analysis with no credential access, and the skill explicitly warns about the SAFEHUB_RULES_REPO trust boundary.

⚠ 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.

0
security
100
transparency
100
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (11)

Pattern match critical

Uses eval() — can execute arbitrary code

CONTRIBUTING.md · code · eval(

Pattern match critical

Accesses sensitive system files

README.md · code · /etc/passwd

Pattern match high

Dynamic Function constructor — equivalent to eval()

rules/execution.yml · prose · downgraded · new Function(

Pattern match medium

References child_process — can spawn system processes

lib/resolve.js · prose · downgraded · child_process

Pattern match medium

Uses exec() — may execute shell commands

rules/execution.yml · prose · downgraded · exec(

Pattern match medium

Uses spawn() — can execute external programs

rules/execution.yml · prose · downgraded · spawn(

Pattern match medium

Base64 decode (atob) — may hide malicious payloads

rules/obfuscation.yml · prose · downgraded · atob(

Pattern match low

Node http/https module — low-level network access

commands/update.js · prose · downgraded · require('https')

Pattern match low

Popular HTTP library — network access

rules/network.yml · prose · downgraded · axios

Pattern match low

Base64 encoding/decoding

rules/obfuscation.yml · prose · downgraded · base64-decode

Pattern match low

Accesses sensitive environment variables

test-fixtures/risky-skill/index.js · prose · downgraded · process.env.SECRET_KEY

Why the tier is capped

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

Permissions & capabilities

Requires 3 system binaries. (1 elevated: git).

package_install

Is this flag fair?

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