Back to skill

Security audit

Swiftverify

Security checks for vulnerabilities and agentic risk

Overview

This is a Swift/SwiftUI project verification skill with no bundled executable code, credentials handling, persistence, or hidden data movement, though its documentation has some inconsistencies users should clarify.

Install only if you are comfortable running local build, lint, and test commands in the target repository. Before using it in CI, confirm which verification entrypoint actually exists and decide whether the generated specs/verification_report.md should be committed or treated as a build artifact.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description is written as a Chinese-only instruction for the skill and does not indicate that users may choose another language or locale. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill's core task says verification is performed by running ./tools/quality_gate.sh full, while the rest of the document presents scripts/run_all.sh as the actual entrypoint and topology root. This creates an intent-level contradiction about what command the skill actually uses to perform its claimed verification workflow.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The documentation says the accessibility guidance is in resources/accessibility-checklist.md, but the earlier declared skill structure lists only resources/ada_checklist.md. This is an active contradiction in the skill's own documentation about what resource backs the accessibility checks.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs generating specs/verification_report.md but does not clearly warn that execution writes into the repository. In agentic or CI contexts, undocumented write behavior can lead to unintended workspace modification, polluted commits, or downstream automation acting on newly created files, especially when users expect a read-only verification step.

Content

No source excerpt is available for this finding.