Back to skill

Security audit

Site Profile

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Markdown alias skill for creating and validating reusable website profiles, with no executable code or hidden persistence.

Install this if you want an alias for website profile authoring and validation. Be aware that it may guide the agent to create reusable project profile data and run validation flows against external sites, so use it only in projects where that behavior is intended.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language invocation guidance is broad enough that ordinary user requests about making a site flow stable or reusable could implicitly trigger this skill without an explicit command. That increases the chance of unintended skill activation, expanding the skill’s authority and making prompt routing less predictable, especially in multi-skill environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example prompt closely resembles a normal task request and can overlap with routine site-debugging or validation instructions. Because it lacks strong scoping language, it may cause the orchestration layer to select this skill in situations where the user did not intend profile persistence or broader validation behavior.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
For the full detailed playbook, also see:

- `skills/external-site-profile-learning/SKILL.md` in this repository

Static analysis

No suspicious patterns detected.