Back to skill

Security audit

Paper Reading Research Question

Security checks for vulnerabilities and agentic risk

Overview

This is a paper-reading workflow that creates local research-question notes and uses user choice gates before producing recommendations.

Before installing, expect this skill to create or update markdown files under a research-question workspace and to read existing field-map notes. Review generated research claims because the skill depends on the quality of cited papers and supporting evidence.

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
80% 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 103)May include surrounding context.

md
Do not recommend Candidate Angles until the user confirms the Writing Intent.

Start by offering a Guided Choice over plausible Writing Intent profiles from the user's stated goal. Do not ask the user to confirm a single proposed profile.

The user should choose: