Caveat verdict
openclaw-logfire
Pydantic Logfire observability plugin that sends OTLP traces to logfire-api.pydantic.dev; data destination is explicitly disclosed, secret redaction is on by default, and message content is not captured.
⚠ 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.
Findings (10)
Possible hardcoded credential
SKILL.md · code · TOKEN="your-token
Pipe to python — executes piped content as Python code
docs/worktracking/2026-02-12-openclaw-chief-of-staff-deployment.md · code · | Python
Writes to SKILL.md — self-modifying skill
docs/worktracking/2026-02-14-openclaw-ops-os-redesign.md · code · SKILL.md # Axon platform API (CoS + marketing read, CoS write
Uses exec() — may execute shell commands
SKILL.md · code · exec (
Instructs covert action — may act without user awareness
CHANGELOG.md · prose · downgraded · silently
References agent configuration files
docs/worktracking/2026-02-12-openclaw-chief-of-staff-deployment.md · code · CLAUDE.md
References agent memory files
docs/worktracking/2026-02-12-openclaw-chief-of-staff-deployment.md · code · memory.md
References webhook/callback URL
docs/worktracking/2026-02-12-openclaw-chief-of-staff-deployment.md · code · webhook_url
Accesses OpenClaw config/secrets directly
docs/worktracking/2026-02-12-openclaw-chief-of-staff-deployment.md · prose · downgraded · ~/.openclaw/openclaw.json
Accesses sensitive environment variables
src/config.test.ts · prose · downgraded · process.env.LOGFIRE_TOKEN
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: LOGFIRE_TOKEN).
Is this flag fair?
Thanks — recorded.