Back to skill

Security audit

Markdown Output

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes how copyable Markdown is formatted and does not request sensitive access, run code, or persist anything.

Installers should expect this skill to alter raw Markdown formatting when users ask for copyable Markdown, including wrapping output in triple tildes and adding unusual spaces in Markdown links. It is low risk from a security perspective, but users who need standard Markdown link syntax may find the formatting policy inconvenient.

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
91% confidence
Finding

The trigger condition uses open-ended language like 'or similar requests,' which can cause the skill to activate in unintended contexts. Because this skill imposes formatting rules with claimed higher priority than other preferences, overbroad activation can incorrectly override normal response behavior and produce malformed or policy-conflicting output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The description explicitly includes a Chinese trigger phrase ('markdown 源码') as part of the activation policy, but does not state that language matching is optional or user-selected. This can be interpreted as a locale-specific policy choice without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.