bid-document

Security checks across malware telemetry and agentic risk

Overview

This skill is a bid-document writing guide with no active code, hidden access, credential use, network behavior, or persistence.

Safe to install for tender and bid-writing support. Users should avoid sharing unnecessary confidential procurement, pricing, legal, or company qualification materials, and should independently review generated compliance, legal, and commercial commitments before relying on them.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description is broad enough to trigger on many generic bidding- or document-related requests without clear scope boundaries. In an agent environment, this can cause inappropriate auto-invocation, leading the model to apply procurement-specific guidance where it was not intended and potentially expose sensitive business, legal, or strategic content to the wrong workflow.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The usage guidance lists very broad call conditions like writing bids, analyzing tender documents, planning content, strategy, and quality review, but provides no exclusion rules or disambiguation. This increases the chance of over-triggering on ordinary writing, compliance, or planning tasks, which can misroute user requests and cause unintended handling of sensitive procurement or competitive-strategy information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal