Back to skill

Security audit

di-perplexity-style

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed search-and-analysis response template with no executable code, persistence, credential access, or hidden data handling.

Install this if you want a structured, source-heavy search analysis style. Be aware that its default mode may produce long analyses for broad topics such as markets or geopolitics, so invoke the quick mode when you want a shorter answer.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill declares the '完整' mode as the default, which means broad classes of user queries may automatically trigger a complex search-and-analysis workflow without a clearly bounded activation condition. In agent settings, vague default activation increases the chance of unintended tool use, overbroad web searches, and application of this skill in contexts where its assumptions do not fit.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The trigger phrases are short and underspecified, and the specification does not provide scope limits, negative examples, or disambiguation rules. This can cause accidental activation from ordinary phrasing, leading the agent to apply search-heavy or opinionated analysis formatting where a simpler or safer response path was intended.

Content

No source excerpt is available for this finding.