Security audit

Data Knowledge Architect — Model the Meaning Behind Your Data

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local data-modeling workflow that creates review and export artifacts, with no evidence of hidden network access, persistence, or destructive behavior.

Install only if you want an agent to read supplied API/CLI/database contracts and generate local semantic-model artifacts. Review generated files before relying on them, and keep sensitive contracts or schemas out unless they are needed for the modeling task.

A.I.G

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

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.
md
dimensions, measures, and routing. Inject model JSON into `assets/review-template.html`; record

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The document declares lang="zh-CN", which forces a specific language/locale for the skill UI. Under the policy, locale constraints should offer user choice or be clearly justified as region-specific, neither of which appears in this file.
Content: No source excerpt is available for this finding.

Whitespace Padding

Medium

Category: Prompt Injection
Confidence: 70% confidence
Finding: Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
Content: Scanner excerpt · references/ingest.md (reported line 5)May include surrounding context.
md
Normalize supplied interfaces into one complete operation inventory before modeling. | Source | Extract | Grain clues | | ------------- | --------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- | | REST/OpenAPI | path+method operation; parameters/requestBody inputs; 2xx schema outputs | array element is often one row; object is often one resource snapshot | | CLI | subcommand operation; flags inputs; JSON/example output; classify read/write from observed contract | list often yields detail facts; show/get often yields snapshots |

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly instructs the agent to write feedback to amendments.md and regenerate artifacts, but it does not prominently warn the user that workspace files will be modified. This can lead to unexpected file creation or overwriting during normal use, reducing user control and auditability even if the behavior is part of the intended workflow.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.