Security audit
aimpact
Security checks for vulnerabilities and agentic risk
Overview
This skill fetches AI news from documented API endpoints and optionally sends the generated report through user-configured messaging, with no hidden install or persistence behavior found.
Install if you trust the ME News API endpoints listed in sources.md. If enabling scheduled push, confirm the configured message channel first because generated news reports may be sent outside the agent session; the skill itself does not store channel credentials.
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.