Back to skill

Security audit

Effector Ecosystem

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Effector ecosystem guidance package, with minor documentation cautions around geolocation, locale examples, and broad audit wording.

Safe to install for Effector-related work. When using generated examples, confirm before adding geolocation, adapt locale values to the project audience, and keep the documented storage guidance: do not put secrets in browser storage and validate persisted data.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The markdown lists geolocation as a useful browser signal, but does not include any caution that location access is privacy-sensitive or may trigger browser permission prompts. For markdown files, safety-relevant behaviors affecting user privacy should be disclosed explicitly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file says to use the playbook when the user asks for a “full audit”, “best practices audit”, or similar review requests, but it does not define exclusions or a tighter scope. Those phrases are broad and common in normal review workflows, which could cause the skill to be invoked in situations beyond the intended Effector-specific production audit context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example sets <html lang="en">, which is natural-language locale policy embedded in the skill content. The file does not indicate that English is optional, user-selected, or required for a region-specific use case, so it can be read as forcing a specific language setting by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
62% confidence
Finding

The i18n section directs implementers to store and react to language values, but does not mention offering users a language choice or obtaining locale preference from the user. Because policy violations include forcing a specific language without user opt-in, this omission can create a risk of non-compliant implementations.

Content

No source excerpt is available for this finding.