Security audit

Customer Segmentation

Security checks across malware telemetry and agentic risk

Overview

This skill fits its CRM segmentation purpose, but it under-discloses sensitive OKKI credential reuse and plaintext local storage of raw customer data.

Install only if you intend this skill to access your OKKI CRM account and local OKKI config/token files. Use least-privileged OKKI credentials, review or override OKKI_WORKSPACE and ENV_PATH, run dry-run and small --limit batches before --confirm, and treat the generated data and logs directories as sensitive customer data that should not be committed, backed up broadly, or shared.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Context-Inappropriate Capability

Medium

Confidence: 94% confidence
Finding: In --sample mode, the script spawns another local script via execSync and forwards the entire process environment. That expands this file’s effective privilege boundary from local JSON generation to arbitrary child-process execution with inherited secrets or credentials, which is unnecessary for producing strategy output and increases the blast radius if the sibling script or environment is compromised.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The script writes raw customer, order, and follow-up records to local JSON files in predictable paths under data/ and logs/. These datasets likely contain sensitive business and personal information, and storing them unencrypted with no access control, minimization, or retention controls increases the risk of local disclosure, accidental commit, backup exposure, or misuse by other processes on the host.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.exposed_secret_literal (+1 more)

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/strategy-output.js:260

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/customer-data-collector.js:21

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/tag-sync.js:33

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/customer-data-collector.js:79

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/tag-sync.js:82

Sensitive-looking file read is paired with a network send.

Warn

Code: suspicious.potential_exfiltration
Location: scripts/customer-data-collector.js:70

Sensitive-looking file read is paired with a network send.

Warn

Code: suspicious.potential_exfiltration
Location: scripts/tag-sync.js:73