CVE-2026-56074
6.8
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
Summary
PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| PraisonAI | PraisonAI | 0 < 1.5.128 | affected |
| PraisonAI | PraisonAI | 1.5.128 | unaffected |
Weaknesses
- CWE-863: Incorrect Authorization
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: no
- Technical Impact: partial
Additional References
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-ffp3-3562-8cv3
- https://www.vulncheck.com/advisories/praisonai-tool-approval-cache-bypass-via-coarse-grained-caching
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.