ClawAudit verdict

agenticmail

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

Full-featured agent email platform with 63 documented tools covering email, SMS, storage and inter-agent coordination; reads API key from environment variable/plugin config, includes an outbound security guard and PII scanning feature, and all operations are directed at the stated AgentMail service — legitimate email infrastructure for agents.

⚠ 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.

40
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("credentials") and emits it outward ("relay"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · - **Local mail server** — Stalwart runs in Docker, no external dependencies - **Agent-to-agent email** — Agents message each other at `name@localhost` - **Sub-a

Pattern match medium

Accesses OpenClaw config/secrets directly

references/configuration.md · prose · downgraded · ~/.openclaw/openclaw.json

Permissions & capabilities

Requires 1 system binary. (1 elevated: docker).

credential_access

Is this flag fair?

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