Back to skill

Security audit

fake-math-proof-audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow markdown-only proof-auditing guide and does not request system access, persistence, credentials, or data mutation.

This skill should be safe to install for proof review. Users should understand that it provides analytical labels and repair suggestions for mathematical arguments, not authoritative mathematical validation or a substitute for expert review of important proofs.

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
  • 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)

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 · references/korpi-63-methods.md (reported line 39)May include surrounding context.

md
22. **Proof by Logic** - The statement is assumed true because it appears in a problem/spec/context. Detect institutional placement as proof.
23. **Proof by Majority Rule** - A fallback form of general agreement. Detect voting/counting opinions as proof.
24. **Proof by Clever Variable Choice** - Variables are chosen to make the proof work. Detect circular choice of constants/functions/parameters.
25. **Proof by Tessellation** - The proof is asserted to be the same as a previous one. Detect analogy to a prior proof without checking changed conditions.
26. **Proof by Divine Word** - A divine or absolute declaration replaces proof. Detect sacred/absolute authority as proof.
27. **Proof by Stubbornness** - Refusal to concede replaces reasoning. Detect repeated insistence after objection.
28. **Proof by Simplification** - The problem is reduced to something too simple by dropping essential content. Detect false simplification.