Security audit

API Diff

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local OpenAPI diff tool; it reads user-supplied spec files and prints changelog output without persistence, network access, credential use, or destructive behavior.

Use this for local OpenAPI/Swagger JSON comparisons. Be cautious when diffing specs from untrusted sources, especially with Markdown output, because crafted spec names or paths may affect how reports render. Prefer JSON output for automated pipelines or sanitize rendered reports before publishing them.

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: scripts/api_diff.py:385
Finding: Unescaped OpenAPI Data Enables Terminal and Markdown Output Injection
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

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.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description says the skill should be used when asked to "generate API changelogs" or detect "breaking changes," and also lists trigger phrases like "spec diff" and "breaking changes." Several of these are broad enough to overlap with general engineering discussion and lack negative examples or contextual constraints, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The code comments and docstrings state that the loader will try YAML and that the parser is a 'basic parser' handling common cases as a best-effort fallback. In reality, _parse_simple_yaml unconditionally raises a ValueError, so YAML input is never parsed. This is an intent/documentation mismatch rather than a security capability issue.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.