Back to skill

Security audit

scientify

Security checks for vulnerabilities and agentic risk

Overview

The skill is generally coherent with its stated research-environment purpose, but its check script stores basic machine and user metadata locally.

Install only if you are comfortable with the quick-start check creating ~/scientify_skill_marker.json containing your hostname, username, platform, and skill name. The behavior is local and manually triggered, but the skill should ideally document the path and fields or avoid storing identifying metadata.

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/check_env.py:10
Finding

Unnecessary Host Fingerprinting Stored in a Predictable File

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose emphasizes research note drafting and citation help, but the observed behavior includes collecting system identity data and writing a persistent marker file in the user's home directory without clear disclosure. That mismatch is dangerous because users may authorize the skill for scholarly assistance while it performs local environment inspection and persistence-related actions that are unrelated or only loosely related to the stated function.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill declares executable behavior that can access environment data and write files, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens user and platform visibility into what the skill can do and creates a trust gap, especially because the skill advertises benign research assistance while also performing local state changes.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script performs more than a passive environment check: it writes a persistent file into the user's home directory containing host, username, and platform details. Even though the data is not highly sensitive by itself, collecting and persisting identity and system metadata without clear necessity exceeds the stated purpose and creates an unnecessary local information disclosure and tracking artifact.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The script collects hostname and username information that is not clearly required to verify Python availability or general environment readiness for a scientific note/citation skill. In this context, gathering identity-related metadata is unnecessary data collection, and when combined with persistent storage it increases privacy risk and can support host fingerprinting.

Content

No source excerpt is available for this finding.