Back to skill

Security audit

Benefits Decoder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for reviewing employment benefits and does not request hidden access, run code, persist data, or contact external services.

Installers should treat this as a benefits-review helper, not professional legal or financial advice. It may handle sensitive salary, equity, health, and family-context details, so users should share only the documents and facts needed for the review.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use the skill when someone asks 'is this offer good' or 'what should I ask HR before signing', which are common conversational phrases and not narrowly scoped commands. The trigger guidance does not include exclusions or tighter context boundaries, so it may overlap with ordinary discussion and invoke the skill too broadly.

Content

No source excerpt is available for this finding.