Back to skill

Security audit

Session Snapshot

Security checks for vulnerabilities and agentic risk

Overview

This skill is for saving and restoring sessions, but it automatically persists conversation history and context without enough controls over sensitive data.

Review this carefully before installing. It may be useful if you want resumable sessions, but you should only enable it where stored snapshots are protected, redacted, easy to delete, and restored only after explicit confirmation. Avoid using it in sessions that may contain credentials, personal data, or confidential workspace details unless those controls exist.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:11
Finding

Unprotected Persistence of Potentially Sensitive Session Data

Content
View full analysis
Remediation
View remediation
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 (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that it periodically saves conversation history, tasks, and context every 30 minutes, but it does not warn users that potentially sensitive data will be persisted. This creates a privacy and data-handling risk because users may disclose secrets, personal information, or workspace context without informed consent, while the skill automatically stores that information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The user-facing description and instructions are presented entirely in Chinese, with no indication that the user can choose another language or that the skill is region-specific. This can violate language or locale policy when a skill imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manual trigger phrase "用户说'保存快照'" is broad and lacks explicit activation boundaries, confirmation, or anti-spoofing constraints. In a conversational system, ambiguous triggers can cause unintended snapshot saves when the phrase appears in quoted text, examples, or adversarial prompt content, leading to unnecessary capture of conversation and context data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The restore section describes loading the latest snapshot and restoring conversation context without warning that restored state may contain stale, incorrect, or sensitive information from earlier interactions. Reintroducing such context can confuse later decisions, revive expired secrets, or expose prior user data in a new conversational state.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The restore flow uses inconsistent phrases ("恢复上一个快照" vs. later "恢复快照") and does not specify authorization, recency checks, or confirmation before loading prior state. This can allow accidental or malicious reintroduction of stale context, causing the agent to act on outdated assumptions or re-expose previously stored sensitive information.

Content

No source excerpt is available for this finding.