Truncus Email

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If invoked with the wrong recipient, content, attachment, or schedule, the agent could send an unintended email using the user's Truncus account.

Why it was flagged

The skill instructs the agent to call an external email-sending endpoint, which is the stated purpose but can create irreversible outbound communications.

Skill content
POST https://truncus.co/api/v1/emails/send
Recommendation

Use this skill only when the user has clearly requested an email send, and review recipient, subject, body, attachments, and schedule before sending important messages.

What this means

A misconfigured or over-scoped key could allow unintended email sending from the associated account or domain.

Why it was flagged

The skill requires a bearer API key to send mail through the user's Truncus account; this is expected for the integration but is still sensitive authority.

Skill content
The API key is read from the `TRUNCUS_API_KEY` environment variable.
Recommendation

Use a least-privilege Truncus key, preferably with only the send scope unless delivery tracking is needed, and avoid exposing the key in prompts, logs, or shared environments.

What this means

Following the wrong repository URL could install content different from the reviewed artifact.

Why it was flagged

The README's manual install URL differs from the listed homepage repository path in the supplied metadata, so users should verify they are installing the intended source.

Skill content
git clone https://github.com/vanmoose/truncus-openclaw-skill.git ~/.openclaw/skills/truncus-email
Recommendation

Prefer installing from the registry artifact or confirm the repository owner and contents before cloning manually.