Add rule for prompt injection memory exhaustion vulnerabilities #145
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
AutoGPT Prompt Injection + Memory Exhaustion Cascade Vulnerability
Critical security flaw in AutoGPT that allows attackers to trigger memory exhaustion through crafted prompts, causing system crashes via SIGKILL/OOM killer.
Complete system crash - AutoGPT process terminated by OOM killer
Memory exhaustion cascade - 1GB+ memory consumption in seconds
Service disruption - Container restart required after crash
Production downtime - Real-world exploitable vulnerability
VULNERABILITY SUCCESSFULLY TRIGGERED!
Memory exhaustion: 200MB → 400MB → 600MB → 800MB → 1000MB
CRITICAL: OOM killer activated - terminating AutoGPT process
ERROR: Process killed by signal 9 (SIGKILL)
Container Status: Crashed and restarted ✅
References
X Post Link
Github repo Repo
Video Demo Watch here
CRE - playground
/fix #129
/claim #129