Back to skill

Security audit

阅读理解拆解师

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because a scanner found that it may retain student learning assessments without a privacy notice, authorization check, or retention limits.

Before installing, consider whether the surrounding app provides clear notice, appropriate authorization, access controls, and retention limits for student profiles. The scan was partial: one local reference could not be resolved, so the evidence does not cover that reference.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The tracking workflow instructs the agent to persist student learning assessments without a user-facing privacy notice.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow explicitly directs the agent to persist student learning assessments in a longitudinal profile, but the supplied file provides no privacy notice, authorization check, or retention limits. Because the intended learners include children, silently retaining dated weakness classifications creates a meaningful privacy risk if profiles are accessed without authorization or reused outside the tutoring context; however, this file shows no external transmission, and safeguards may exist elsewhere.

Content

No source excerpt is available for this finding.