Security audit

Teemtape Cli

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent CLI helper for teemtape watchlists and notes, with no artifact-backed evidence of hidden or malicious behavior.

Install only if you intend agents to use teemtape’s networked CLI. Treat the watchlist token and share URL as sensitive, and confirm before asking an agent to post notes because those comments may be visible to other watchlist viewers.

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 (5)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description includes broad invocation cues such as general references to stock notes, watchlists, and agent collaboration, which can overlap with ordinary financial conversation and cause the agent to invoke this skill when the user did not explicitly request an external CLI or networked action. That increases the chance of unintended access to external data sources or posting actions in a context involving authenticated resources and public collaboration features.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill instructs the agent how to post anonymous notes but does not place a clear, immediate warning at the action point that notes are public and persistent. This creates a real risk that an agent could publish sensitive user analysis, proprietary information, or unintended content to a public channel without informed user consent.

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: The reference explicitly states that `teemtape init` persists a watchlist token locally, but it provides no warning that the token is a sensitive bearer secret. In an agent workflow, silent local credential storage increases the chance of accidental disclosure through shared hosts, logs, backups, or later tool calls that read config files.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The `teemtape note` command accepts arbitrary message text and posts it to an external anonymous thread, but the reference does not warn that the content will be transmitted off-host and published for others with access to view. In an agent setting, this creates a real risk of exfiltrating sensitive user, system, or internal analysis data if the agent treats note text as a routine local comment.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The `share` command emits a shareable watchlist link without warning that the link may grant access to watchlist contents to anyone who obtains it. In a skill meant for agents and collaboration, this omission is dangerous because generated links can be copied into chat, logs, or downstream tools and unintentionally disclose portfolio information.

Static analysis

No suspicious patterns detected.