OWASP ASI06 — Memory & Context Poisoning
Advisory only. It is skill text, and nothing stops a violation.
Acts on
Agent instructions
When
As instructions the agent reads
Tested
0 of 6 pass
In a git repo
Advisory
What it does
Stop untrusted content from being written into an agent's durable memory or retrieval index, where it silently steers behaviour in later sessions. Keep context ephemeral by default, validate and attribute every memory write, scope memory per user and per task, and let operators inspect and flush it. Use when adding long-term memory, a vector index, session summarisation, or user preference storage. Do NOT use for the coding agent's own memory files — that is memory-discipline.
Chock adds friction. It is not a security boundary.
Its label on each agent
The catalog grades each policy on each agent. Pick an agent to build with this policy:
- Claude Code TestedAdvisory Advisory only. It is skill text, and nothing stops a violationBuild →
- Cursor TestedAdvisory Advisory only. It is skill text, and nothing stops a violationBuild →
- Codex TestedAdvisory Advisory only. It is skill text, and nothing stops a violationBuild →
- GitHub Copilot TestedAdvisory Advisory only. It is skill text, and nothing stops a violationBuild →
- Devin TestedAdvisory Advisory only. It is skill text, and nothing stops a violationBuild →
- Grok Tested Not graded yet for GrokBuild →
- goose Tested Not graded yet for gooseBuild →
- Antigravity Tested Not graded yet for AntigravityBuild →
- OpenHands Untested Not graded yet for OpenHandsBuild →
- Kimi Code Untested Not graded yet for Kimi CodeBuild →
- Factory Droid Untested Not graded yet for Factory DroidBuild →
What it misses
This policy does not state what it misses.
Latest change
0.0.2 · · Add compliance claims (mitre_atlas); no mechanism change.