Back to skill

Security audit

Temp Mail Pro

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign with medium confidence: the findings are treated as purpose-related, though the scan reports automatic legal-confirmation records, an unpinned installer, and incomplete reference resolution.

The verdict is benign, not a guarantee of safety. Before installing, consider the unpinned installer and the reported automatic legal-confirmation record, and note that some referenced paths were unresolved, so the scan evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

Compliance logging could support a temporary-mail skill, but this code does more than log an operation: it unconditionally asserts that legal confirmation occurred. That substantive behavior is not described and is not supported by any confirmation interaction in the supplied chunk. The mismatch is this automatic confirmation recording, not merely the absence of mailbox functionality in a partial code sample.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skillhub'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation command invokes an unpinned npm CLI through npx, potentially downloading and executing a changing package version with the installing user's privileges. Although this is not an MCP server declaration, a compromised publisher or malicious future release could execute code and access local files or credentials.

Content

No source excerpt is available for this finding.

The mandatory consent gate requires Chinese-language confirmation without user opt-in.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The confirmation rules accept only specified Chinese phrases and explicitly reject English “yes,” preventing users from proceeding unless they confirm in Chinese. This imposes a language requirement without offering a language choice or documenting a justification for the restriction.

Content

No source excerpt is available for this finding.

Batch-operation reminders are triggered by ordinary words without requiring a bulk-data context.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The keyword list includes “全部” (all), “所有” (every/all), and “循环” (loop), which commonly occur in requests unrelated to bulk data collection. No contextual matching requirement or exclusions are specified, so ordinary requests can unnecessarily trigger the batch-collection warning and confirmation flow.

Content

No source excerpt is available for this finding.

The confirmation rules require Chinese-language consent without offering a language choice.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

Every accepted confirmation is Chinese, while “yes” is explicitly rejected and the fallback prompt directs users to enter “同意”. This imposes a language constraint on consent without user opt-in or a documented reason that consent must be expressed in Chinese.

Content

No source excerpt is available for this finding.

The consent gate requires Chinese confirmation wording and explicitly rejects English “yes,” without offering a language choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The accepted confirmations are exclusively Chinese, while English “yes” is explicitly rejected as ambiguous. This imposes a language restriction on users without opt-in; requiring explicit legal consent does not justify rejecting equally explicit confirmation in another language.

Content

No source excerpt is available for this finding.

The out-of-scope handling instruction mandates a Chinese-language reply without user language opt-in.

Low
Category
Output Handling
Confidence
93% confidence
Finding

The instruction tells the agent to reply directly with a fixed Chinese sentence whenever an unsupported capability is requested. Unlike merely documenting the skill in Chinese, this prescribes user-facing output in a specific language without a language choice or documented locale justification.

Content

No source excerpt is available for this finding.