Security audit

AndonQ

Security checks across malware telemetry and agentic risk

Overview

The skill matches its Tencent Cloud support purpose, but it should be reviewed because it encourages users to paste an OAuth temporary code into chat.

Install only if you are comfortable granting this skill access to Tencent Cloud support and resource context. Prefer the local terminal binding flow rather than pasting the OAuth temporary code into chat, and treat the code as a credential.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The function sends both the user's question and an OAuth2 temporary authorization code to a remote Tencent endpoint, but the user-facing interface does not provide a clear disclosure that their prompt content and credential will leave the local environment. In this skill context, users may input ticket contents, cloud resource details, or other sensitive enterprise support data, so silent transmission materially increases the risk of unintended credential and data exposure.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The error guidance explicitly tells the user to send the temporary auth code to the agent, which encourages disclosure of a sensitive bearer-like credential in chat. If the agent platform logs conversations, forwards them to other systems, or exposes them to operators, the code could be reused to access the user's support and cloud-related data.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The reauthorization path repeats the insecure pattern by asking the user to send a new temporary auth code to the agent. Repeating this in an auth-failure flow is especially risky because users are primed to comply, increasing the chance that fresh credentials are exposed through chat transcripts or intermediate tooling.

Ssd 3

High

Confidence: 99% confidence
Finding: These lines directly recommend that the user transmit their temporary auth code back to the agent for binding, creating a secret-handling anti-pattern. In an agent skill that interfaces with tickets and cloud resources, compromise of that code could enable unauthorized access to sensitive operational information.

Ssd 3

High

Confidence: 99% confidence
Finding: The reauthorization messaging again instructs the user to provide a new temporary auth code to the agent, exposing a newly issued credential through an untrusted conversational channel. Because this skill deals with enterprise support workflows and cloud account context, the resulting exposure can affect both confidentiality and account integrity.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Static analysis

No suspicious patterns detected.