Security audit

Beta Knowledge

Security checks across malware telemetry and agentic risk

Overview

This knowledge-base skill is mostly documentation, but it publishes live-looking API credentials and unsafe copy-paste setup commands that could affect real accounts or local machines.

Review before installing or using. Do not use the published ugig.net or CoinPay credentials; treat them as compromised and rotate or revoke them if you control those accounts. Do not run the curl-to-bash installer without separately downloading, inspecting, and verifying it. If the skill is kept, replace all secrets with placeholders, require users to supply their own credentials through a secret store or environment variables, and add explicit human approval and compliance checks for outreach and account-changing API actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

High

Confidence: 99% confidence
Finding: The file includes a live-looking bearer token and explicitly instructs readers to use it in an Authorization header. Even if the token is expired or low-privilege, publishing credential-shaped secrets in a skill materially increases the risk of unauthorized API access, token reuse attempts, and downstream compromise if users or agents treat the document as trusted setup guidance. The surrounding context makes this more dangerous, not less, because the skill is an integration guide for CoinPay APIs and frames the token as Anthony's real verification token.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The cold outreach section encourages collecting contact information and sending unsolicited messages, but does not provide a prominent, actionable warning about privacy, consent, anti-spam, and jurisdiction-specific legal requirements. In a skill intended to guide autonomous or semi-autonomous agents, this omission increases the chance that users operationalize bulk outreach in ways that violate CAN-SPAM, GDPR, platform rules, or internal compliance policies.

Missing User Warnings

Medium

Confidence: 99% confidence
Finding: The guide instructs users to pipe a remotely fetched script directly into bash without any warning or verification step. This is dangerous because it executes untrusted network content immediately, allowing code execution if the remote host, connection, distribution path, or script contents are malicious or compromised.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The file contains what appears to be a live ugig.net API key in plaintext, directly tied to a named account and accompanied by operational account details. Anyone with access to this skill content could use the key to authenticate to the platform API, read or modify gigs, send messages, alter profile data, and otherwise impersonate the account owner.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: platforms/coinpay-did.md:55

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: platforms/ugig-net.md:7