Panews

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  0.2.2

Overview

This skill is a purpose-aligned PANews crypto news reader; the main caution is that its broad auto-invocation wording could route generic news requests to PANews unexpectedly.

Install if you want an agent to use PANews as a crypto/blockchain news source. Be aware that broad prompts like "latest news" or "what happened today" may activate this skill and return PANews crypto coverage unless your agent asks for clarification.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill enables implicit invocation but does not define narrowly scoped trigger conditions or clear boundaries for when the agent should call it. Because this skill covers broad cryptocurrency news, rankings, searches, events, and editorial content, an agent may invoke it unexpectedly in loosely related conversations, creating overreach, unintended data access patterns, or manipulation of user workflow through unsolicited tool use.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases are broad enough to match generic browsing requests such as asking about columns or topic areas, which can cause this skill to activate when the user did not specifically intend to use PANews. In an agent routing context, overbroad triggers can misroute users, cause irrelevant tool use, and increase exposure to downstream actions or external content without sufficiently clear user intent.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrases are broad enough to match generic event-related requests that may not clearly indicate the user wants PANews crypto industry events. In an agent-routing context, this can cause over-activation of the skill, leading users to be steered into cryptocurrency-specific content when they asked for general events, which is a scope and trust boundary issue rather than direct code execution.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger examples are very broad and include common phrases like 'Latest news' and 'What just happened,' which can easily match ordinary user requests without sufficient scoping. In an agent environment, this can cause unintended invocation of the PANews skill, leading to misrouting, unnecessary external data access, and reduced reliability of responses, even if it does not directly create code-execution risk.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The trigger is broad enough that the skill may activate for generic requests like 'What happened today?' without clearly distinguishing itself from other news or market-summary skills. In an agent setting, this can cause incorrect tool routing, unnecessary external data access, and user confusion, though it is not a direct code-execution or injection issue.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The request helper supports sending a PA-User-Session header to the remote PANews API, but this CLI file provides no user-facing disclosure, consent prompt, or minimization around when session credentials are transmitted. In an agent skill context, silent propagation of session tokens to a third-party service increases the risk of credential misuse, over-broad authenticated access, and accidental leakage through future command additions.

VirusTotal

57/57 vendors flagged this skill as clean.