Security audit

Buffer Calculator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local lab buffer calculator, but its core recipe calculations are badly wrong and its declared file/tool permissions are broader than its documentation admits.

Review before installing or using in a lab. Do not rely on its recipe outputs without independent verification, and prefer a corrected version with fixed unit conversions, explicit reagent forms, input validation, and narrower tool permissions.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (4)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/main.py:53
Finding: Incorrect Unit Conversion Produces Solid Quantities 1,000 Times Too Large
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: scripts/main.py:25
Finding: Ambiguous Reagent Forms and Percentage Units Can Generate Incorrect Chemical Instructions
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/main.py:43
Finding: Unvalidated Numeric Inputs Permit Negative, Non-Finite, and Unrealistic Recipes
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Note

Location: SKILL.md:4
Finding: Skill Declares Filesystem and Command Capabilities Beyond Its Functional Requirements
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (3)

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill claims 'No file access' and presents a low-risk profile, but the manifest explicitly allows Write/Edit/Bash and the documentation describes creation of output files. This mismatch can mislead users or downstream policy systems into granting too much trust, increasing the chance that file-modifying behavior is used without appropriate scrutiny or restrictions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The natural-language labels "上游" and "下游" introduce a locale-specific element in the skill description, but the document does not indicate that multilingual output is optional or user-selected. This can conflict with a language/locale policy requiring user opt-in before forcing a specific language.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.