Security audit

bolo-jiimore

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Amazon market-research skill that sends product keywords and filters to LinkFoxAgent, with no evidence of hidden or destructive behavior.

Install only if you trust LinkFoxAgent with your Amazon product-research keywords, filters, target markets, and API usage. Prefer setting the API key only for the current session or via a proper secrets manager, do not print it in shared logs or screenshots, and avoid submitting confidential product plans unless the provider's data handling terms are acceptable.

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 (4)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The README says the skill activates for broad prompts like Amazon market research or product selection, which can cause the agent to invoke external marketplace analysis for ordinary user requests without clear scoping or consent. In an agent setting, overly broad activation increases the chance of unintended tool use, unnecessary data transmission, and user confusion about when third-party services are contacted.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The README states the skill automatically translates keywords and queries marketplace data, but does not warn that user inputs may be sent to an external API. This creates a transparency and privacy issue: users may provide proprietary product ideas, strategy terms, or sensitive business research queries without realizing they are being transmitted off-platform.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The skill instructs users to query an external API and maps natural-language requests into API parameters, but it does not clearly warn that user-provided keywords, market selections, and possibly derived business-intelligence queries will be transmitted to a third-party service. This creates a privacy and transparency issue, especially if users enter sensitive commercial research terms or internal product ideas.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The documentation explicitly tells users to print the API key with `echo $LINKFOXAGENT_API_KEY`, which can expose the secret on shared terminals, screen recordings, shell transcripts, CI logs, or support screenshots. While this does not itself transmit the key externally, it materially increases the chance of credential disclosure through common operational practices.

Static analysis

No suspicious patterns detected.