Back to skill

Security audit

Answer Book

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk local “answer book” that returns a random short answer and does not access sensitive data or persist changes.

Installers should treat this as an entertainment skill. The main practical caveat is that it may respond to broad “guidance” or oracle-style prompts, so users who want ordinary advice may need to be explicit.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation description includes generic activators like "guidance," "needs a yes/no/wisdom-style answer," and "oracle," which could match many ordinary user requests not intended to invoke this specific skill. The trigger list also lacks negative examples or clear boundaries for when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instructions require the agent to pick English or Chinese according to the user's detected language and state "Never mix languages in a single answer," which imposes a locale behavior without explicit user opt-in. The policy allows language handling when the user is offered a choice or the constraint is clearly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file explicitly sets 'Default language: en', and the CLI argument also defaults to English unless the user overrides it. The policy requires avoiding forced language or locale choices unless the user is given a choice or the default is clearly justified; here, the default preference is imposed rather than prompted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.