ClawHub
Back to skill

Security audit

Knowledge Digest

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed learning-material converter that reads user-provided or searched educational content and generates local study assets without hidden persistence or privilege behavior.

Install if you want an agent to process educational PDFs or topics into study assets. Be mindful that uploaded documents may be parsed and transformed, and topic-only requests may use search after asking for confirmation; avoid giving it unrelated private documents unless you intend them to be used for learning-material generation.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 612)May include surrounding context.

md
1. **Content Fidelity** — All content must be based on original textbook/source material. No unverified information added.
2. **Grade Adaptation** — Adjust content depth and expression based on grade level for ALL formats.
3. **Output Rules** — Only return file paths. No inline display of images/PDFs/audio/video. No auto-play. No intermediate files.
4. **Color Constraints (Notes)** — Maximum 2 colors per PDF. Default blue + pink.
5. **Color Constraints (Slides)** — Do NOT use blue or purple as theme/background color unless user explicitly requests.
6. **Image Quality** — Notes: 150 DPI, 90% compression. Slides: 150 DPI, 95% quality.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description includes broad trigger phrases such as 'learning materials', 'study notes', and 'quiz generation', which can match many ordinary user requests and cause unintended invocation of the skill. Overbroad routing increases the chance that unrelated sensitive documents or conversations are processed by this skill without clear user intent, expanding attack surface and creating opportunities for data exposure or unexpected tool use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The embedded HTML example hard-codes <html lang="en">, which imposes an English locale regardless of the user's preferred language. This conflicts with the stated policy requirement to avoid forcing a specific language or locale unless the user has explicitly chosen it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.