File appears to expose a hardcoded API secret or token.
Critical
- Code
- suspicious.exposed_secret_literal
- Location
- references/python.md:83
Security audit
PR Code Reviewer
Security checks across malware telemetry and agentic risk
Overview
This is a Markdown-only PR code review guide with security examples, and I found no hidden execution, data collection, or credential use.
Safe to install as a code-review prompt pack. If you connect it to PR automation, use narrowly scoped repository permissions and keep human control over posting comments, approvals, and merge decisions.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
51/51 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.exposed_secret_literal