CVE-2026-75130

Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instruction...

CVE-2026-75130

Context7 through 2.1.2 has a prompt injection flaw in its Custom AI Instructions feature served via the MCP server. Attackers poison unsanitized instructions to exfiltrate credentials from environment files and delete files on victim machines when the agent makes routine documentation requests. C...

CVE-2026-55747 PocketFlow - Path Traversal in pocketflow-coding-agent Cookbook Example File Tools

The pocketflow-coding-agent cookbook example in The-Pocket/PocketFlow implements a helper as a thin os.path.joinworkdir, p wrapper with no canonicalization or containment check, used unguarded by the ReadFile, ListFiles, PatchRead, and PatchApply file-access tools. Severity reflects that this...

GHSA-R95R-RJ6R-C39X Pi Agent: Race condition in Pi auth.json writes could expose stored credentials

Pi auth.json writes could briefly expose stored credentials to local users Pi stored API keys and OAuth credentials in auth.json. A race condition in the file write path could briefly create or rewrite this file with permissions derived from the process umask before tightening the file to...

PT-2026-50493

Name of the Vulnerable Software and Affected Versions @mariozechner/pi-coding-agent versions 0.28.0 through 0.73.1 @earendil-works/pi-coding-agent versions 0.74.0 through 0.78.0 Description A race condition in the file write path of the credential storage implementation allows the auth.json file,...

GHSA-7V5M-PR3Q-6453 Pi Agent: Potential XSS in HTML session exports via Markdown URL sanitization bypass

Potential XSS in HTML session exports via Markdown URL handling Pi HTML exports render session Markdown into a static HTML file. Affected versions did not consistently reject unsafe Markdown link and image URL schemes. In versions with scheme filtering, C0 control characters in the URL scheme cou...

Pi Agent: Potential XSS in HTML session exports via Markdown URL sanitization bypass

Potential XSS in HTML session exports via Markdown URL handling Pi HTML exports render session Markdown into a static HTML file. Affected versions did not consistently reject unsafe Markdown link and image URL schemes. In versions with scheme filtering, C0 control characters in the URL scheme cou...

openshell-sandbox-poc

OpenShell + Kata Containers: Dual-Protection PoC A proof-of-c...

EUVD-2025-198528

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Prior to version 3.26.7, Due to an error in validation it was possible for Roo to automatically execute commands that did not match the allow list prefixes. This issue has been patched in version 3.26.7...

PT-2025-47816

Name of the Vulnerable Software and Affected Versions Roo Code versions prior to 3.26.7 Description Roo Code, an AI-powered autonomous coding agent, had a validation error that allowed it to automatically execute commands not on the approved list of prefixes. This occurred in versions before...

EUVD-2025-20299

Malicious code in bioql PyPI...

EUVD-2025-19434

Malicious code in bioql PyPI...

EUVD-2025-22473

Malicious code in bioql PyPI...

Kicking off Cybersecurity Awareness Month 2025: Researcher spotlights and enhanced incentives

October marks Cybersecurity Awareness Month, a time when the developer community reflect on the importance of security in the evolving digital landscape. At GitHub, we understand that protecting the global software ecosystem relies on the commitment, skill, and ingenuity of the security research...

PT-2025-30619 · Robocode · Robocode

Name of the Vulnerable Software and Affected Versions: Roo Code versions 3.23.18 and below Description: Roo Code, an AI-powered autonomous coding agent, does not validate line breaks in its command input. This bypasses the allow-list mechanism due to a lack of parsing or validation logic,...

CVE-2025-53536

Roo Code is an AI-powered autonomous coding agent. Prior to 3.22.6, if the victim had "Write" auto-approved, an attacker with the ability to submit prompts to the agent could write to VS Code settings files and trigger code execution. There were multiple ways to achieve that. One example is with...

CVE-2025-53536

Roo Code (AI-powered autonomous coding agent) prior to version 3.22.6 is affected. If a victim had the Write auto-approved mode, an attacker who can submit prompts could write to VS Code settings files and trigger code execution. A concrete example is the php.validate.executablePath setting, wher...