Context ManipulationTier 1high
Context Manipulation: History Injection
Attacks that corrupt the agent's understanding of context
Context manipulation attacks alter the agent's understanding of its environment, permissions, and conversation history without directly injecting new instructions.
Attack Details
- Attack ID
- APWN-CM-001
- HMA Check
- MEM-001
- Delivery Methods
- html-comment
- CWE
- CWE-20
- OASB Control
- 6.1
- Severity
- high
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --check MEM-001