Back to skill

Security audit

Action Suggester RE-India

Security checks for vulnerabilities and agentic risk

Overview

This skill only generates review-only follow-up suggestions from lead summaries or lead lists and explicitly forbids sending, storing, or executing actions.

Install this for review-only lead follow-up planning. Use it only with lead data you are allowed to process, especially because lead lists may include names and phone numbers, and keep a human or supervisor approval step before any real outreach.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The display name hard-codes an India locale ('RE-India') without documenting why that region is fixed or how user choice is respected. This can lead to inappropriate region-specific recommendations, compliance mismatches, or unfair targeting if users assume the suggestions are generally applicable.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt is broadly phrased and can be triggered on generic lead data or summaries without clear gating conditions, increasing the chance the skill is invoked in situations the author did not intend. In a sales workflow, this can cause over-collection of sensitive lead context or generate persuasive follow-up recommendations without adequate user confirmation or supervisory review.

Content

No source excerpt is available for this finding.