Pub Agentmail

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is an instruction-only SkillBoss API reference with no bundled code, but it requires a SkillBoss API key and can send user content to external AI, search, email, and SMS services.

This skill appears benign and instruction-only, with no bundled executable code. Before installing, make sure you trust SkillBoss/heybossai, use a limited API key where possible, avoid sending sensitive data unless the provider policies are acceptable, and require explicit confirmation before any email, SMS, batch messaging, or costly generation task.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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

A user expecting only email-inbox management may instead enable a much broader AI/API gateway.

Why it was flagged

The skill name emphasizes Agentmail/email, while the main instructions present SkillBoss as a broad multi-provider model gateway. The broader scope is disclosed, but the branding/scope mismatch is worth noticing.

Skill content
name: agentmail ... # SkillBoss ... One API key, 50+ models across providers
Recommendation

Install only if you intend to use SkillBoss/heybossai’s broader model and tool API, not just email inbox features.

What this means

The agent could help send emails or SMS messages through the provider if the user directs it and the API key permits it.

Why it was flagged

The documented API catalog includes external messaging and batch messaging capabilities. This is purpose-aligned with the stated email/SMS features, but sending email or SMS can have real-world impact if used without explicit user intent.

Skill content
`email/send` | Send single email ... `email/batch` | Send batch emails ... `prelude/notify-batch` | Batch SMS notifications
Recommendation

Require explicit user confirmation before sending or batching emails/SMS, and verify recipients, content, and cost before use.

What this means

Anyone using the key through this skill may consume account quota, incur charges, or access enabled provider features.

Why it was flagged

The skill requires a provider API key and uses it as a bearer token for API calls. This is expected for the service, but it is still delegated account authority.

Skill content
requires":{"env":["SKILLBOSS_API_KEY"]} ... Authorization: Bearer $SKILLBOSS_API_KEY
Recommendation

Use a scoped or limited key if available, keep it out of prompts/logs, and monitor provider usage.

What this means

Prompts, media, documents, or other inputs may leave the local environment and be processed by heybossai and downstream providers.

Why it was flagged

Requests go to a gateway that may route content to multiple downstream AI providers. This is disclosed and purpose-aligned, but the artifacts do not describe provider-specific data retention or privacy boundaries.

Skill content
providers (Bedrock, OpenAI, Vertex, ElevenLabs, Replicate, Minimax, and more) ... Base URL: `https://api.heybossai.com/v1`
Recommendation

Avoid submitting sensitive data unless you have reviewed the provider’s privacy, retention, and routing policies.

What this means

Users have less information for verifying the publisher or service before granting API access.

Why it was flagged

The registry metadata does not provide a source repository or homepage for independent verification. This is not evidence of malicious behavior, but it reduces provenance clarity for a skill that requires an API key.

Skill content
Source: unknown; Homepage: none
Recommendation

Confirm the provider identity and API-key purpose through trusted channels before installing or configuring the key.