Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | "Show meeting details" | `query_meetings.js` |
Security audit
tencent-meeting
Security checks for vulnerabilities and agentic risk
Overview
The skill mostly does what it claims, but it can use enterprise Tencent Meeting credentials to create meetings and access recordings/transcripts with broad triggers and limited consent warnings.
Install only if you intend this skill to use Tencent Meeting enterprise API credentials. Treat transcript and recording operations as sensitive: confirm the meeting, user ID, authorization, and sharing destination before retrieving or exposing download URLs or transcript text.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (5)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | "Download meeting recording" | `list_records.js` → use download URLs |
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 96% confidence
- Finding
The skill invokes local Node scripts that necessarily use environment variables for Tencent credentials and make outbound API calls, yet the manifest does not declare any tool scope such as allowed tools or permissions. This weakens policy enforcement and user visibility around secret access and network use, increasing the chance the skill is invoked with broader capabilities than intended.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The description includes broad trigger phrases such as 'schedule a meeting', 'meeting transcript', and 'meeting recording', which are generic intents that may overlap with other calendar, conferencing, or note-taking skills. This can cause unintended invocation of a skill that accesses enterprise meeting data and recordings, leading to accidental disclosure or modification of sensitive resources.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill provides workflows for listing recordings, retrieving download URLs, and extracting meeting transcripts but does not warn that these artifacts may contain highly sensitive business, personal, or regulated data. In this context, missing warnings and consent cues are more dangerous because the skill is specifically designed to access recordings and transcripts, making accidental over-collection or disclosure more likely.
- Content