Security audit
readme-writer-skill
Security checks for vulnerabilities and agentic risk
Overview
This skill is a README-writing aid made only of Markdown guidance and reference files, with no executable code or hidden access.
This is reasonable to install as a documentation-writing skill. Before publishing a generated README, review badges, links, installation snippets, and any curl-based commands for accuracy and safety because they may be copied by future readers.
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
Static analysis
No suspicious patterns detected.