Security audit

Data Source Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a construction data-audit helper whose file access and Excel export are purpose-aligned, though users should scope inputs and sanitize spreadsheet exports.

Before installing, confirm you want the agent to handle construction project metadata and local files you provide. Use explicit file paths, avoid broad project-directory scans unless intended, and sanitize or review untrusted survey values before exporting Excel/CSV catalogs, especially values beginning with =, +, -, or @.

A.I.G

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: SKILL.md:518
Finding: Spreadsheet Formula Injection in Excel Catalog Export
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill description and instructions are broadly framed around 'construction data processing and analytics' and 'comprehensive audit of all construction data sources and systems' without clear activation boundaries. That increases the chance the skill will trigger for generic construction-data requests and then direct the agent to follow SKILL.md-defined methods and APIs, potentially causing over-broad data handling or unintended use of sensitive project information.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description promises a comprehensive audit that includes creating an integration roadmap. In the provided implementation, the code can catalog sources, score quality, identify silos, and emit high-level recommendations, but it does not generate a roadmap object, phased plan, timeline, or dependency-based sequencing that would substantiate the roadmap claim.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The documentation states that the method creates data sources from survey responses, which implies using the survey-provided source details. However, the implementation populates many source attributes but omits the survey template's integrations field, meaning the documented discovery behavior is broader than what the code actually captures.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This markdown file includes executable sample code that creates data_catalog.xlsx via to_excel, which writes data to the local filesystem. The surrounding documentation does not warn that running the example will create or overwrite a file, so users are not clearly informed about this data-affecting behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This manifest file describes a "Comprehensive audit of all construction data sources and systems" but does not define any specific trigger phrases, scope boundaries, or negative examples. In a manifest, such broad wording can create ambiguous invocation conditions and increase the chance of unintended activation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.