ClawHub
Back to skill

Security audit

Email Quality Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped email-audit helper that reviews evidence and explicitly avoids sending email or changing provider settings.

Install this if you want an evidence-based email campaign or program audit. Be prepared to provide sensitive marketing evidence such as consent, suppression, engagement, provider, and outcome data, and verify before authorizing any audit artifact to be saved.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The activation guidance is broad enough to trigger on generic requests like checking whether an email campaign is safe, which can cause the host agent to invoke this skill in situations where a narrower or different skill may be more appropriate. Over-broad invocation increases the chance of unintended data access, mis-scoped analysis, or user-confusing autonomous routing, especially in multi-skill environments.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 110)May include surrounding context.

md
## Persistence

Persist only after explicit authorization to `memory/audits/email/YYYY-MM-DD-<topic>.md`. Preserve the scorer's orthogonal `status` and `verdict`; validate the complete v3 draft with `validate-audit-artifact.py` against the intended `--relative-path`, persist only through one full-content Write, and revalidate the target per the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Do not autonomously modify consent, claims, provider settings, or hot cache.

## Reference Materials

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The display name, summary, and description embed Chinese text by default, indicating a mixed-language presentation regardless of user preference. This can violate language or locale policy when no opt-in or language selection behavior is documented.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.