ClawHub
Back to skill

Security audit

List Hygiene Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed email-list hygiene assistant that reads subscriber engagement and suppression data to produce reports and worklists, with memory writes gated on user permission.

Install only if you are comfortable giving the agent access to email engagement exports, bounce/complaint data, and suppression history. Review any generated prune/suppress worklist before applying it in your ESP, since the skill produces recommendations rather than safely executing account changes itself.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The display name, summary, and description embed Chinese text directly with no indication that the user can choose language or locale. This creates a natural-language locale policy concern because the skill imposes bilingual output/branding rather than offering an explicit language preference or documenting a justified region-specific constraint.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Save Results

After delivering, ask "Save these results for future sessions?" If yes, write the hygiene report + the segmented worklist and the reusable SEND-`S`/`E` summary to `memory/email/list-hygiene-monitor/YYYY-MM-DD-<list-or-topic>.md` — see [skill-contract.md §Save Results Template](../../../references/skill-contract.md) — so the next scheduled run can trend against it. Promote hygiene blockers and the `S`/`E` reads to `memory/hot-cache.md` and add unresolved fixes (suppression leakage, an over-benchmark trend) to `memory/open-loops.md`. Do not write memory without asking.

## Reference Materials
Confidence
75% 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.

Static analysis

No suspicious patterns detected.