Back to skill

Security audit

IDX Stock Profile Scraper

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public company profile data from the Indonesia Stock Exchange and does not show hidden, destructive, persistent, or credential-stealing behavior.

Reasonable to install if you are comfortable with a skill that makes live requests to the IDX website and returns English-normalized field names. For stricter environments, consider pinning dependency versions and treating the broad security/VirusTotal claims as publisher assertions rather than guarantees.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description states that the skill 'Automatically translates all field keys from Indonesian to English,' which imposes a language transformation by default. This is a natural-language locale policy concern because the skill does not indicate any user opt-in, configurability, or justification for forcing English output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The request headers hard-code Accept-Language: en-US,en;q=0.5, which imposes an English/US locale preference regardless of user preference or environment. This is a natural-language/locale policy concern because the skill does not document any user opt-in or justification for forcing that locale.

Content

No source excerpt is available for this finding.

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
91% confidence
Finding

The dependency manifest allows any requests version at or above 2.32.5 instead of pinning to a specific known-safe release, making it impossible to verify from this file alone which version will actually be installed in different environments. While the lower bound likely avoids many older CVEs, the unpinned specification still creates supply-chain uncertainty and can unintentionally pull in a future vulnerable or incompatible release.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.