ClawAudit verdict
dream-of-clawra
get-up
Accesses credentials AND makes external network calls
Sends semantically-selected image URLs from a CDN to messaging channels; the workflow is transparent (user triggers, image selected, sent via OpenClaw), with no credential exfiltration or hidden behavior evident in the content.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
package_install
Findings (3)
Possible hardcoded credential
scripts/clawra-selfie.sh · prose · downgraded · TOKEN="${OPENCLAW_GATEWAY_TOKEN:-}
References child_process — can spawn system processes
bin/cli.js · prose · downgraded · child_process
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
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
No declared permissions — minimal attack surface.
network_outcredential_accesspackage_install Thanks — recorded.