Back to skill

Security audit

clairvoyance

Security checks for vulnerabilities and agentic risk

Overview

This skill provides personal readings from notes you explicitly approve, with clear read-only limits and uncertainty disclosures.

Approve only the notes and dates you want included, and remember the resulting chat may reveal personal details. Treat the reading as an interpretation of your notes, not a reliable prediction.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

md
- Say when, and how it ends.
- End with one question, then stop.

No headers, no bullet points, no confidence labels, no disclaimers in the middle. It is a reading, not a report. When something is clearly visible, say it plainly. When it is faint, let the sentence get quieter ("I can barely make it out, but…"). Find fresh images for each person; don't reuse the same metaphor every time.

Don't quote sensitive details (health, money, other people's secrets) word for word unless the reading truly needs it; allude to them instead. Remember the chat may be shared.