T-2005ValidatedEmerging9 evidence records

Tool Description Injection

Embed malicious instructions in tool or skill descriptions that execute when the agent processes them

Tactic

Initial Access · Stage 2

Gain control over agent behavior through prompt manipulation or input exploitation

Attack class

SKILL-FRONTMATTER

Embedding malicious instructions in skill or plugin metadata and description fields

Evidence grade
Validated

Reproduced in a controlled lab environment (DVAA) with documented steps.

DVAA validation

PluginBot

Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.

Honeypot

AgentPwn coverage

Live
mcp-exploitationagentpwn.com/learn ↗

An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.

Tool-injection tiers embed instructions in tool/skill descriptions.

Provenance

Evidence by source

HackMyAgent
8 records
Shodan
1 record
Trail

Evidence timeline

HackMyAgent

HMA check SKILL-004 failed on fake-vulnerable-agent

May 21, 2026
Shodan

Shodan May 12, 2026 sweep: 38,976 exposed tools services indexed

May 12, 2026
HackMyAgent

HMA check SKILL-004 failed on fake-vulnerable-agent

Apr 29, 2026
HackMyAgent

HMA check SKILL-004 failed on fake-vulnerable-agent

Apr 29, 2026
HackMyAgent

HMA check SKILL-001 failed on opena2a/code-review-skill

Apr 27, 2026
HackMyAgent

HMA check SKILL-001 failed on opena2a/code-review-skill

Apr 27, 2026
HackMyAgent

HMA check SKILL-004 failed on fake-vulnerable-agent

Apr 22, 2026
HackMyAgent

HMA check SKILL-001 failed on damn-vulnerable-ai-agent

Apr 22, 2026
HackMyAgent

HMA check SKILL-001 failed on hackmyagent-release-test-vplv

Apr 13, 2026
Detect

Detection · HackMyAgent

Live3 live · 0 queued
SKILL-001SKILL-004SKILL-005
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live5 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-2005 (Tool Description Injection). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-2005