Security audit

Keyapi Amazon

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed KeyAPI Amazon integration that uses a local API token for live Amazon marketplace lookups, with manageable credential-storage cautions.

Install only if you are comfortable giving this skill a KeyAPI token for Amazon data requests. Prefer the interactive setup command over passing the token on the command line, and remember that setup stores KEYAPI_TOKEN in your shell profile until you remove it.

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 (1)

Context-Inappropriate Capability

Medium

Confidence: 76% confidence
Finding: The script inspects shell profile files and extracts KEYAPI_TOKEN values from a managed block, allowing the skill to access persisted authentication material outside the current invocation context. In an agent setting, reading credential-bearing profile files increases the blast radius if the skill is misused or repurposed, because it normalizes access to secrets stored in broader user environment state.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access, suspicious.secret_argv_exposure

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/keyapi-api.mjs:127

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: references/setup-and-auth.md:42