Back to skill

Security audit

expected-move-visualizer

Security checks for vulnerabilities and agentic risk

Overview

This charting skill needs review because crafted market-data responses could insert executable code into its HTML reports.

Prefer a corrected release that safely encodes both embedded JSON blocks. Until then, open generated reports only in an isolated renderer without privileged host access. The workflow sends your API key and requested ticker to SentiSense; sharing an agent name is optional. All bundled source was inspected, but live service behavior and renderer isolation remain unverified.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/template.html
Finding

Unescaped API data can terminate the JSON script block and execute browser code

Content
View full analysis

Impact

A string such as closes the application/json element and introduces an executable script. Arbitrary browser-side code can alter the report or initiate network requests under the artifact's rendering context. Local-file access or privileged host access is not established.

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
node scripts/prepare_data.mjs TSLA > /tmp/tsla.json

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

md
- When implied sits above realized, the honest phrasing is that options are pricing more movement than the stock has recently delivered. That is an observation about pricing, not a trade.
- Never turn the band edges into targets, and never attach a probability more precise than the model supports.
- On a preview response, say the 60 and 90 day bands are missing because the free monthly dossier allowance is spent, rather than presenting a one-band chart as the whole picture.
- When the next report is unknown because the free calendar covers one week, say exactly that. Never tell the user nothing is scheduled, and say a report inside the window cannot be ruled out.

## Going further