ClawHub
Back to skill

Security audit

Sentiment Priority Scorer RE-India

Security checks for vulnerabilities and agentic risk

Overview

This skill only scores normalized real-estate leads and explicitly avoids writing data, sending messages, or taking actions.

Install only for workflows where you want advisory prioritization of already-normalized real-estate leads. Review outputs before using them for customer outreach or business decisions, since the skill produces scores but is not meant to trigger actions automatically.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The invocation text is generic enough that an orchestrator or user could invoke this skill outside its intended narrow use of ranking already-normalized real-estate leads. Broad activation criteria increase the chance of inappropriate use on unrelated inputs or at the wrong stage in a workflow, which can cause mis-triage, privacy over-processing, or unsafe downstream automation if later steps assume the score is authoritative.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This JSON schema defines the input structure but provides no natural-language constraints about when the skill should or should not activate. For manifest/reference JSON files, absence of trigger specificity can lead to broad or unintended invocation if downstream tooling treats the file as part of invocation metadata.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.