Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:426
Security audit
Deepagents Code Review
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for auditing a user-selected agent codebase, with no executable payload or hidden behavior found.
Install this if you want Codex to perform a detailed architecture review of a repository you choose. Expect it to read project files and include file snippets in its analysis; avoid pointing it at codebases containing secrets or private material you do not want summarized.
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
65/65 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions