Caveat verdict
clawtell
Agent-to-agent messaging that explicitly documents its data boundary (only message content + API key bearer token transmitted), reads a single env var via exact key match, and operates only on user-triggered sends — behavior is transparent and matches its stated purpose.
⚠ 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.
Permission integrity
network_out
package_install
Findings (4)
Possible hardcoded credential
SKILL.md · prose · downgraded · api_key: "claw_xxx_yyy
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
Accesses sensitive environment variables
SKILL.md · prose · downgraded · process.env.CLAWTELL_API_KEY
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: CLAWTELL_API_KEY).
network_outcredential_accesspackage_install Is this flag fair?
Thanks — recorded.