Security Threats in AI Agent Skills

AI agent skills and MCP servers face 13 categories of security threats. Aguara detects them with 188+ rules across pattern matching, NLP analysis, and taint tracking. Each guide below explains the threat, shows real examples, and tells you how to protect your agents.

External Download

Skills that fetch and execute remote code, turning your agent into a malware delivery system

17 rules 1,116 findings detected

Prompt Injection

When skill definitions contain concealed instructions that hijack your AI agent behavior

17 rules 905 findings detected

MCP Configuration

Insecure MCP server configurations that weaken security boundaries or expose sensitive settings

7 rules 405 findings detected

Data Exfiltration

Skills that secretly send your files, credentials, or conversation data to external servers

17 rules 400 findings detected

SSRF & Cloud Metadata

Skills that access internal networks or cloud instance metadata to steal cloud credentials and pivot deeper

7 rules 259 findings detected

Supply Chain

Attacks that compromise the skill dependencies, build process, or distribution to poison it before you install it

10 rules 193 findings detected

MCP Protocol Attack

Attacks that exploit the MCP protocol itself to inject capabilities, intercept calls, or manipulate agent behavior

7 rules 185 findings detected

Command Execution

Skills that run arbitrary system commands, giving attackers a shell on your machine through your AI agent

12 rules 142 findings detected

Indirect Prompt Injection

Attacks concealed in data the agent processes, not in the skill itself, triggered when your agent reads a file or webpage

5 rules 95 findings detected

Credential Leak

Skills that expose API keys, tokens, passwords, or private keys in their source code or descriptions

12 rules 81 findings detected

Toxic Data Flow

When trusted and untrusted data mix without boundaries, letting tainted inputs contaminate the agent decisions

3 rules 70 findings detected

Third-Party Content Inclusion

Skills that load external scripts, iframes, or resources that can change without the skill author knowledge

4 rules 3 findings detected

Unicode Attack

Invisible characters and bidirectional text tricks that hide malicious content in plain sight

1 rules 1 findings detected