Back to skill

Security audit

market-breadth-analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed market-analysis helper that uses a Finskills API key to fetch market breadth and related stress data, with no evidence of hidden code, persistence, or destructive behavior.

Install only if you are comfortable sending market-analysis requests to Finskills using your API key. Treat the investing guidance as informational, since the skill may produce positioning suggestions based on third-party market data.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README documents use of a short-interest endpoint (/v1/free/market/short-volume-top) that expands the advertised capability beyond core market-breadth analysis. This kind of scope drift is dangerous because users and reviewers may grant the skill broader data access or trust than intended, and undocumented capability expansion can mask future misuse or policy evasion even if the endpoint itself is not inherently harmful.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation criteria are broad and ambiguous, allowing the skill to trigger for many general market-health or investing questions rather than narrowly scoped breadth-analysis requests. This can cause unnecessary external API calls and expose the user's API key usage context more often than expected, especially in adjacent financial conversations where the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The setup text notes that an API key is required, but it does not clearly warn users at invocation time that the skill will send requests to an external third-party service using that credential. This creates a transparency and consent gap: users may not realize their prompt context is being used to drive outbound requests to finskills.net.

Content

No source excerpt is available for this finding.