Back to skill

Security audit

User Guide Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward web-app documentation workflow, with the main practical risk being careful handling of credentials and sensitive screenshots.

Install only if you want an agent to explore a web app and write a screenshot-heavy Markdown guide. Prefer test accounts or pre-authenticated sessions, limit the requested scope, and review screenshots before sharing the output because they may show private app data.

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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md
- `browser_press(key=...)`
- `browser_console(clear=true)` after navigation or significant interaction

For pages with animations, lazy loading, or scroll-revealed content, do not judge a section from one viewport alone. Scroll in small increments, pause briefly, then re-check with `browser_snapshot()` and/or `browser_vision()` before deciding content is missing or empty.

During exploration, collect only the UI details needed for the guide:
- page title

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly solicits credentials for use in browser-driven exploration but provides no safeguards on secret handling, minimization, redaction, or prohibition on storing credentials in generated artifacts. In a workflow that captures screenshots and writes detailed documentation, this increases the risk of exposing passwords, session data, or other sensitive access details during execution or in output files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction 'Write formal Indonesian' imposes a specific language requirement. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation unless the skill offers a choice or clearly documents a justified region-specific constraint.

Content

No source excerpt is available for this finding.