OpenHuman: Indirect prompt injection via background email sync executes Composio actions without user approval
Affects OpenHuman versions before 0.57.13 where Gmail or another supported provider is connected via Composio and background sync is active, which is the default. Fixed in 0.57.13.
Written by anthropic/claude-haiku-5.5 from the sources below. Verify against them.
- Exploited
- Proof of concept public, per CISA
- Fix
- Fixed in 0.57.13
- Who is exposed
- Default setups
Do first: Check every install: default setups are affected.
- Last modified
- A 0-100 score for how much a CVE matters across the industry: exploitation, exposure, how widely the software is used, severity and whether a fix exists.What do these mean? →
- 47/100 · provisional
- How many real-world setups can hit the bug, from the vendor's advisory and CISA data. It does not know your setup.What do these mean? →
- Default setups
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
- Exploitation: poc
- Automatable: no
- Technical impact: total
Summary
OpenHuman, an open-source agent harness for desktop and Rust use, can be tricked into running third-party actions through connected services such as email, Slack, and Notion. An attacker can reach this remotely, without logging in, by delivering crafted content to a connected account, which can lead to sending or forwarding data, posting messages, changing third-party content, or disclosing information from OpenHuman memory and integrations.
Read the original description
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13.
cve.now Index
- Exploitation15/40CISA rates a proof of concept as public
- Exposure22/25Default setups, reachable over the network without a login
- Reach?/20Unknown. No tracked technology or package matched
- Severity9.7/10CVSS 8.7, total technical impact per CISA
- No patch0/5No signal
What would change the score
- Would score about 72 if added to CISA KEV
- Would score about 67 if CISA's SSVC rates exploitation active
What to do
Check every install: default setups are affected.
Upgrade to a fixed version: 0.57.13.
Timeline
- CVE published
- First seen by cve.now
- CISA SSVC assessment
Exploitation: poc · Automatable: no · Technical impact: total
- Record last updated
Affected versions
- tinyhumansai openhuman
fixed in 0.57.13
Evidence 4
- Advisory
- Repository
- Repository
- Repository
Corrections
None so far.
Something wrong on this page? Report an error. Every fix is listed here.
Questions about CVE-2026-54142
Is CVE-2026-54142 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. CISA's SSVC assessment notes a proof of concept exists. No public exploit code is tracked.Source: cve.now feed data
What does this mean?
Crafted content delivered to a connected account can make OpenHuman's background agent invoke Composio actions without user approval. The stated impacts include sending email, posting messages, modifying third-party content, and disclosing memory contents and stored credentials.Source: github.com
Which versions are affected by CVE-2026-54142?
openhuman: before 0.57.13.Source: cve.now feed data
Am I affected, and how do I check?
Versions before 0.57.13 are affected, in setups where a supported provider such as Gmail is connected via Composio and the background email, Slack, or Notion sync is active, which is the default configuration. To check, compare the installed OpenHuman version with 0.57.13 and review whether Composio connections and background sync are enabled.Source: github.com
How do I fix CVE-2026-54142?
Upgrade OpenHuman to version 0.57.13 or later.Source: github.com