Security audit

Sql To Dashboard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned SQL-result visualization guide with no hidden runtime behavior, credential access, persistence, or destructive actions found.

Reasonable to install if you want help turning provided SQL output into chart specs. Review outputs when using very large result sets, because the documentation allows aggregation or sampling, and note that some repository support files still reference an older skill name.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (8)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The declared purpose is about data visualization from SQL query results. The actual code chunk is unrelated to SQL or visualization; it is a QA/test script for a skill package. Its primary behavior is reading SKILL.md and repository files, validating documentation conventions, and scanning for secrets. This is a materially different purpose and introduces undeclared capabilities around repository inspection and compliance testing. Therefore the description does not accurately represent the code.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The instruction 'Keep SKILL.md body in English' imposes a language constraint in natural language. This is a locale/language policy restriction, and the file does not present it as optional, user-selectable, or justified as a region-specific requirement.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The statement 'SKILL.md body must be in English; reference docs in English' is a hard language-policy requirement. Under the policy, forcing a specific language without user choice or a documented rationale is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation description 'SQL query or result set + chart/dashboard/visualize intent' is not a specific trigger phrase list and does not define boundaries for when the skill should or should not activate. Terms like 'chart' and 'visualize' are broad enough to overlap with many ordinary analytics requests, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The mandatory rules state 'Do not change the query — work with exactly what the user provides' at L125, but the example of a good output for very large results says to 'Aggregate or sample' and report 'showing top 100' at L158. That creates an intent-level contradiction in the skill documentation about whether transforming the provided results is allowed.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The reference file names a different skill (user-provides-sql) than the manifest (sql-to-dashboard), indicating documentation/packaging inconsistency. While not directly exploitable on its own, this mismatch can cause the wrong reference material to be associated with the skill, increasing the risk of operator confusion, incorrect behavior, or accidental trust in unrelated instructions if the skill bundle is consumed automatically.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring says this is an auto-generated test suite for skill user-provides-sql, while the provided manifest context is for the sql-to-dashboard skill. This is an active documentation contradiction about what artifact the file belongs to, which can mislead maintainers and reviewers about the skill being tested.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.