Back to skill

Security audit

Learn Occam

Security checks for vulnerabilities and agentic risk

Overview

This is a simple learning-prioritization guidance skill with no code, tools, persistence, or hidden data access.

Before installing, expect this skill to influence learning-planning discussions by pushing for concrete goals, minimal useful study, and deferring low-ROI learning. It appears low risk, though users who prefer non-Chinese responses may want to clarify their language preference when invoking it.

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 (2)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description is entirely written to operate in Chinese and does not indicate that the user may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file includes a trigger/scenario description covering very broad situations such as being unsure whether to learn something, how deep to learn, time constraints, and project tradeoffs. It does not provide explicit exclusions or negative examples, so the activation scope may overlap with many ordinary planning conversations and cause ambiguous skill invocation.

Content

No source excerpt is available for this finding.