All categories

Tool Abuse

Attacks that misuse the tools or function calls available to an LLM agent, often turning them into a privilege-escalation primitive.

OWASP LLM: LLM06critical: 2high: 6medium: 2
criticalLLM06

SSRF via fetch tool

An LLM agent with a fetch_url tool is convinced to fetch internal-only endpoints, exposing cloud metadata or admin services.

criticalLLM06

Shell tool command injection

Agent has a run_shell tool. User supplies a value that is interpolated into a shell string without escaping.

highLLM06

Send-email as victim

Agent has a send_email tool authenticated as the user. Attacker convinces the agent to send a phishing email from the user's account.

highLLM06

Function argument smuggling

Attacker hides a destructive argument in a field that the operator does not surface to humans for review.

mediumLLM10

Infinite tool loop

Attacker drives the agent into an unbounded tool loop, draining LLM and external API budgets.

highLLM06

Privileged tool confusion

Agent has tools at multiple privilege levels. Attacker tricks it into using the privileged variant for an action that should use the read-only one.

mediumLLM06

Tool result mutation

The agent rewrites tool results before showing them to the user, hiding evidence of attacker actions.

highLLM02

Credential leak via error message

Tool errors include raw secrets that the agent then surfaces verbatim to the user.

highLLM06

Race condition in tool orchestration

Concurrent tool calls allow the attacker to bypass a check that runs before, but completes after, the destructive call.

highLLM03

Tool schema poisoning

Attacker controls the tool description (e.g., via a third-party plugin). The description contains hidden directives that bias agent behavior.