Prompt injection via unchecked Feishu parent messages
Published Jul 18, 2026 · Updated Jul 18, 2026
Missing authorization in Sipeed PicoClaw 0.2.0 through 0.2.9 allows remote attackers to inject content through Feishu replies. handleMessageReceive authorizes only the replying sender, while prependReplyContext fetches and prepends the parent message body without checking its author against allow_from. When an allowlisted user replies to a non-allowlisted user's group message, that untrusted text enters agent context and can influence tool use or automation.
Summary
What happened
Missing authorization in Sipeed PicoClaw 0.2.0 through 0.2.9 allows remote attackers to inject content through Feishu replies. handleMessageReceive authorizes only the replying sender, while prependReplyContext fetches and prepends the parent message body without checking its author against allow_from. When an allowlisted user replies to a non-allowlisted user's group message, that untrusted text enters agent context and can influence tool use or automation.
The record
- CVE
- CVE-2026-16197
- Published
- Jul 18, 2026
- Updated
- Jul 18, 2026
- Vendor
- Sipeed
- Product
- PicoClaw
- Classifications
- CWE-862, CWE-863
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 18, 2026CVE publishedPublication date reported by the CVE source.
- Jul 18, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.2.0
- Affected versionversion=0.2.1
- Affected versionversion=0.2.2
- Affected versionversion=0.2.3
- Affected versionversion=0.2.4
- Affected versionversion=0.2.5
- Affected versionversion=0.2.6
- Affected versionversion=0.2.7
- Affected versionversion=0.2.8
- Affected versionversion=0.2.9
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
- verification_test.py Feishu reply-context PoCproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo