Security audit

伙伴个人需求登记

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it records confirmed personal work requests into a company Teable table, but it requires careful handling of a Teable access token.

Install only if you are comfortable sending a short-lived, tightly scoped Teable token through your IM/agent flow. Use the minimum scopes listed, restrict it to the intended Teable space, delete the token message after setup, and remove or rotate the token if the workspace or chat history may be exposed.

SkillSpector

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 (2)

Ssd 3

High

Confidence: 98% confidence
Finding: This skill explicitly instructs the agent to ask the user for a Teable personal access token over IM and then persist it to a local file. Even though it acknowledges chat-retention risk, collecting a long-lived secret through chat and storing it in workspace state materially increases the chance of credential disclosure via message history, logs, filesystem access, backups, or later prompt/tool exfiltration.

Ssd 3

Medium

Confidence: 93% confidence
Finding: The skill directs the agent to persist personal identity data and operational configuration into USER.md and MEMORY.md for reuse across sessions. While it avoids storing the token itself, it still creates unnecessary durable records of employee identifiers, team membership, and system configuration in broadly readable workspace files, increasing privacy exposure and making future sessions more likely to act on stale or over-broad authority.

Static analysis

No suspicious patterns detected.