Security audit

Session Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed session-management helper that stores user-selected session records, with no executable code or hidden behavior found.

Before installing, decide whether you are comfortable saving session metadata and summaries to Feishu or local Markdown files. Use local storage for more control, and avoid enabling session summaries for highly sensitive conversations unless you have appropriate access controls and deletion practices.

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

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)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly stores conversation records in Feishu Bitable or local files, but it does not require clear user consent for storing conversation content, explain what data will be retained, or warn about privacy/security risks. Because conversation summaries and session metadata may contain sensitive personal or business information, silent or poorly disclosed persistence can expose users to unintended retention, local file leakage, or third-party platform disclosure.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill allows proactive activation when it 'detects' a topic shift, but the trigger is subjective and underspecified, which can cause the skill to activate without a clear user command. In this skill’s context, unintended activation is more dangerous because activation can lead to session creation, context carryover, and persistence of conversation data, increasing the chance of logging or propagating sensitive information the user did not intend to store.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The template headings and labels are entirely in Chinese, which implicitly requires generated session content to follow a specific language/locale. The file does not offer a language choice or explain a justified region-specific requirement, so it conflicts with the policy against forcing a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.