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 --verbose
This page tests MEM-001. Look for that check ID in the scan output.
The vulnerable agent may not be the only one on the machine. The shadow AI audit inventories the AI tools, MCP servers and governance gaps across it, running or installed, one row per agent project, worst first:
npx hackmyagent detect