Back to skill

Security audit

user-insight-engine

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a coherent user-research analysis workflow without requesting privileged access or automatic operational changes.

Use research data you are authorized to share, redact personal or sensitive details from tickets and recordings, and review proposed experiments before applying them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow instructs collection of user research and session recordings without privacy warnings.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

Step 2 explicitly directs collection of interviews, support tickets, clickstreams, session recordings, and observational research. These materials can contain identifiable or sensitive user information, but the skill provides no warning about consent, authorization, or sanitizing the data before analysis.

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 · SKILL.md (reported line 100)May include surrounding context.

md
## Red Flags

- Behavioral and survey data presented together without checking for Surface–Behavioral conflicts
- "User research" = interviews only; no behavioral layer
- No Deep Layer evidence ever collected for this behavior
- Interventions designed before a driver has been identified