Back to skill

Security audit

Docs Sync

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-maintenance helper whose repository reads, doc edits, navigation updates, branch commits, and optional GitHub issue creation fit its stated purpose.

Install this if you want an agent to inspect repository changes and keep documentation current. Use review-first mode when you want to approve proposed edits before files are changed, and be aware that direct-apply mode can modify documentation files, update doc-site navigation, and create a local branch commit; issue mode can create a GitHub issue using your authenticated gh session.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown skill description explicitly tells the agent to write doc updates, edit files, commit to a branch, and possibly modify navigation/config files. While it mentions a 'Review first' option, the overall description does not clearly warn users that running the skill may change repository content and create commits, which can affect user data and system state.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The instruction 'Commit to a branch — never push directly to main' imposes a specific workflow choice in natural language. Although not a language-selection issue, this does not match the defined SQP-3 policy scope, so it should not be reported unless it concerns language or locale; therefore no valid SQP-3 finding is present.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.