Security audit

Specification Extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to read user-provided construction specification documents and produce structured summaries, with minor dependency and scoping cautions.

Install only if you are comfortable granting filesystem access for the documents you choose to process. Use a virtual environment, avoid running dependency installation as administrator/root, and consider pinning `pdfplumber` before use. Keep prompts scoped to construction specification extraction and provide only files intended for analysis.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:415
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction "When the user asks to convert or extract data" is broad and underspecified, which can cause the skill to activate on loosely related prompts and process files or paths without clear scope checks. In a skill that accepts file paths and external project data, ambiguous triggering increases the chance of unintended data handling, overbroad parsing, or abuse through crafted requests that appear to be simple extraction tasks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.