ClawHub
Back to skill

Security audit

Promo Stack

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill provides promo inventory, ad pacing, pre-order copy, and supplier email templates without installing code, accessing credentials, or taking actions automatically.

Installers should expect this skill to produce operational recommendations and ready-to-use customer or supplier messaging for promo stock-risk situations. Review any ad pause recommendations, pre-order language, ship-date claims, and supplier emails before publishing or sending them, especially where legal pre-sale rules or agency approval rules apply.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are intentionally expansive and include vague phrases like using the skill whenever users mention low inventory, oversell risk, safety stock breaches, or multi-channel inventory sync. That breadth can cause unintended invocation in routine operations conversations, leading the agent to generate operational copy, supplier comms, or ad-pause guidance in contexts where the user did not explicitly request those actions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · SKILL.md (reported line 42)May include surrounding context.

md
Include **at least one** complete **supplier chase email** (subject + body) with merge fields:

- SKU / variant IDs, quantities, required-by date, PO reference, incoterm or ship-to if relevant, escalation line ("if no confirmation by …").

Optional second template: **SMS/Slack one-liner** for internal ops.

Static analysis

No suspicious patterns detected.