PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-56835 MervinPraison CVE debrief

CVE-2026-56835 is a high-severity vulnerability in PraisonAI, a multi-agent teams system, affecting versions from 3.11.0 to before 4.6.59. The issue allows unauthorized users to trigger configured PraisonAI agents via Slack app_mention events, bypassing user and channel authorization settings. This occurs because the Slack bot applies its configured allowed_users, allowed_channels, and unknown-user pairing policy in the normal Slack message event handler but not in the adjacent Slack app_mention event handler.

Vendor
MervinPraison
Product
PraisonAI
CVSS
HIGH 8.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-23
Original CVE updated
2026-10-29
Advisory published
2026-10-23
Advisory updated
2026-10-29

Who should care

Defenders responsible for PraisonAI deployments, especially those with restricted access controls, should assess their exposure and take necessary remediation steps. Slack administrators and security teams monitoring Slack channel activity should also be aware of this vulnerability.

Why it matters

CVE-2026-56835 is a high-severity vulnerability in PraisonAI that allows unauthorized users to trigger configured agents via Slack app_mention events, bypassing user and channel authorization. Defenders should prioritize verifying exposure, applying compensating controls, and upgrading to version 4.6.59 or later. Evidence is limited to CVE and source item details.

  • Potential unauthorized triggering of configured PraisonAI agents by users or in channels not explicitly allowed
  • Bypass of user and channel authorization settings for Slack app_mention events
  • Possible unintended actions by PraisonAI agents due to unauthorized triggers
  • Need for verification of PraisonAI instance exposure and compensating control implementation

Technical summary

The vulnerability exists in PraisonAI's Slack bot implementation, where the app_mention event handler does not apply the configured authorization settings (allowed_users, allowed_channels, and unknown-user pairing policy) unlike the normal message event handler. This discrepancy allows unauthorized users to trigger PraisonAI agents in channels where the bot is present, potentially leading to unintended actions.

Defensive priority

Defenders should prioritize verifying exposure of PraisonAI instances, especially those with restricted user and channel access, and apply compensating controls like monitoring for unusual activity.

Recommended defensive actions

  • Verify PraisonAI instance exposure, especially for restricted user and channel access
  • Monitor for unusual activity in Slack channels where PraisonAI is present
  • Apply compensating controls to restrict unauthorized agent triggering
  • Upgrade to PraisonAI version 4.6.59 or later
  • Review and implement additional compensating controls for exposed systems
  • Conduct thorough monitoring and detection for potential exploitation attempts
  • Track and document remediation efforts and exceptions for affected assets

Evidence notes

The CVE record and source item provide details on the vulnerability, affected versions, and patch information. However, additional information on potential exploitation or specific attack scenarios is limited.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-56835 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-56835

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-56835 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-56835

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.