GHSA-5c3v-h6hw-4gx7: Duplicate Advisory: PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
This advisory was withdrawn on Oct 8, 2026. The publisher no longer considers it a valid vulnerability.
Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-4r3p-w3mc-5v34. This link is maintained to preserve external references. Original Description PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously.
Published Jul 10, 2026 · Updated Oct 8, 2026
Affected packages
praisonai
- Ecosystem
- PyPI
- Affected
- <= 4.6.77
- Fixed in
- No patched version yet
- Check
pip show praisonai
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
Duplicate Advisory
This advisory has been withdrawn because it is a duplicate of GHSA-4r3p-w3mc-5v34. This link is maintained to preserve external references.
Original Description
PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.
References
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-61438
PraisonAI vulnerable to Remote Code Execution via Broken AST Sandbox
high7.3Oct 29, 2026CVE-2026-60085
PraisonAI: SecurityPolicy command/path/import restrictions are completely unenforced by the default SubprocessSandbox backend
high8.7Oct 8, 2026CVE-2026-60086
PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
medium5.3Oct 8, 2026CVE-2026-60088
PraisonAI: Project custom command templates can read outside-workspace files into model prompts
medium5.5Oct 8, 2026CVE-2026-60090
PraisonAI: PGVector and Cassandra knowledge stores interpolate vector dimensions into DDL
mediumOct 8, 2026CVE-2026-60091
PraisonAI: Jobs API is unauthenticated by default and allows attacker-controlled webhook SSRF
high7.2Oct 8, 2026
