Back to skill

Security audit

AI crawler access check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped robots.txt checker that reads public web files and gives user-directed advice without installing code or requesting credentials.

Install this if you are comfortable with the agent fetching a public robots.txt file for a domain you provide and checking crawler documentation. Review any suggested robots.txt changes before applying them, since the skill only advises and does not itself edit your site.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables allow_implicit_invocation without any visible trigger constraints in this file, which can cause the skill to activate in broader conversational contexts than intended. Because the skill reads attacker-influenced URLs or domains to fetch and interpret robots.txt, overly broad automatic invocation increases the chance of untrusted prompt context steering the agent into unintended external access or misleading security conclusions.

Content

No source excerpt is available for this finding.