Back to skill

Security audit

IM智能提醒

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence; the completed scans found no AIG issues, but Skillspector flags three medium-severity scope and reminder-limit concerns.

The verdict is benign, with high confidence, and the scans report complete coverage of the 11 listed components. Before installing, consider whether you are comfortable with the reported scope mismatch and possible extra reminders; benign does not mean risk-free.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

The reminder workflow generates learning content and provides tutoring despite the manifest explicitly limiting it to scheduling, merging, and sending.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest at L003 explicitly states that reminder content is supplied by other skills and is not generated here. However, L173 directs this skill to generate a variant exercise, reinforced by the generation-check reference at L423; L301–L303 additionally direct it to restructure tasks and re-explain material rather than merely manage reminders.

Content

No source excerpt is available for this finding.

The exam-day policy permits an additional reminder outside the daily sending budget.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

The manifest limits delivery to one merged daily summary, but L098 specifies an exam-morning message that does not count against the day's budget. This creates an explicit budget exemption that permits an additional notification alongside the regular summary, despite L100 stating that exam preparation must not increase message counts.

Content

No source excerpt is available for this finding.

Reminder defaults allow an additional immediate notification beyond the manifest’s single daily summary.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

The manifest limits this skill to consolidating queued reminders into one daily summary. However, L14–L16 configure the daily allowance for upper-primary, middle-school, and high-school students as one summary plus one immediate notification, permitting delivery beyond that stated limit.

Content

No source excerpt is available for this finding.