ClawHub
Back to skill

Security audit

sales-enablement

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only sales-collateral skill with disclosed, purpose-aligned guidance and no executable, persistent, or hidden behavior found.

Install this if you want help drafting sales enablement materials. Review outputs for accuracy, especially pricing, ROI, proof points, customer claims, and any context pulled from product-marketing files.

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
93% confidence
Finding

The skill description contains many broad trigger phrases such as 'sales materials,' 'help my sales team,' and 'what should I give my sales reps,' which can match loosely related requests and cause the wrong skill to activate. Over-broad routing is dangerous because it can pull the agent into producing sales-oriented content for requests better handled by other skills, increasing the chance of context confusion, policy bypass through misclassification, or unintended access to adjacent instructions and files.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The eval explicitly rewards triggering on casual phrasing for a broad sales-enablement skill without defining tighter routing boundaries or required disambiguation. This can cause over-broad activation, misrouting user requests away from more appropriate skills, and increase the chance that unrelated prompts are handled with the wrong templates or assumptions.

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 · references/demo-scripts.md (reported line 129)May include surrounding context.

md
**What to avoid:**
- Showing every feature of this section
- Getting lost in settings or configuration
- Talking for more than 3 minutes without asking a question

---