Add AutoGPT infinite loop memory exhaustion detection rule (CRE-2025-… #140
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…0165) This CRE rule detects when AutoGPT enters an infinite loop during task execution, repeatedly attempting the same actions without memory of previous attempts. The rule identifies the pattern of repeated command execution, failures, and memory exhaustion that characterizes this high-severity production issue. Key detection patterns: - Repeated thought-command-failure sequences within 60s window - Memory usage approaching critical levels (80%+) - Absence of successful task completion markers - Command retry loops without progression Addresses GitHub issue prequel-dev#129 for AutoGPT high-severity failure reproduction.
Contributor
|
Hi @himayday thanks for submitting the CRE! this LGTM, please solve the merge conflict. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
CRE-2025-0165: AutoGPT Infinite Loop Memory Exhaustion Detection
🎯 Overview
This PR introduces a comprehensive detection rule for AutoGPT infinite loop memory exhaustion - addressing critical production failures where AutoGPT agents become stuck in recursive task execution patterns. The rule identifies when autonomous agents lose memory context and repeatedly attempt the same actions, leading to exponential resource consumption and system crashes.
CRE Playground Links
CRE-2025-0165 Playground: Test Rule
📊 AutoGPT Issues Covered
THOUGHTS:.*(?:attempting|trying|executing).*actionMemory usage:.*(?:[8-9][0-9]|100)%COMMAND.*execute_.*(sequential pattern)(?:Failed|Error|Unable to).*(?:execute|complete|perform)🧪 Testing & Validation
Rule Logic
The detection rule identifies the following sequence within a 60-second window:
🎬 Demo Environment
Repo link Repo Link invitation send
Screencast.from.2025-08-29.15-05-34.mp4
🚨 Production Impact Examples
Real-world scenarios covered:
🛡️ Mitigation Strategies
The rule enables detection of:
References
closes #129
/claim #129