Duplicate Advisory: PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
Description
PraisonAI versions up to 4.6.77 have a prompt injection defense misconfiguration where the block threshold is set to block only CRITICAL severity threats. This allows HIGH-level prompt injection attacks to bypass blocking and only be logged. Such attacks can include instruction overrides or financial manipulation, potentially enabling unauthorized extraction of system prompts and tool invocations. The vulnerability has a CVSS score of 7.5, indicating high severity.
CVSS v3.1
Score 7.5high
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
PraisonAI versions <=4.6.77 contain a misconfiguration in their prompt injection defense mechanism. The block threshold defaults to CRITICAL severity, which means that prompt injection attacks classified as HIGH severity are not blocked but merely logged. This allows attackers to perform single-vector prompt injection attacks, such as instruction overrides or financial manipulation, that evade blocking controls. The consequence is potential unauthorized extraction of system prompts and invocation of tools without authorization. The vulnerability is tracked under CWE-1188 and has a CVSS 3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N).
Potential Impact
Attackers can bypass prompt injection defenses for HIGH severity threats, enabling them to extract system prompts and invoke unauthorized tools. Confidentiality is impacted (high impact), but integrity and availability are not affected according to the CVSS vector. This could lead to unauthorized access to sensitive system instructions and manipulation of system behavior.
Mitigation Recommendations
No patch links are provided in the input data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, users should be aware that HIGH severity prompt injection attacks may bypass blocking and consider additional monitoring or compensating controls if feasible.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-5r2q-3wg3-57m2
- Osv Schema Version
- 1.4.0
- Ecosystems
- ["PyPI"]
- Database Specific Severity
- HIGH
- Cvss Version
- 3.1
Threat ID: 6ac6bfad2cdf04f656828beb
Added to database: 10/07/2026, 21:54:53 UTC
Last enriched: 10/07/2026, 21:56:27 UTC
Last updated: 10/07/2026, 21:56:27 UTC
Views: 3
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.