PT-2026-77160

Name of the Vulnerable Software and Affected Versions CodeWhale versions prior to 0.8.64 Description Insufficient validation of file paths in the project config instructions field allows for the reading of arbitrary files on a system. An attacker can use a malicious .codewhale/config.toml file...

PT-2026-77164

CodeWhale codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain an argument injection vulnerability in the git show tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted...

PT-2026-77159

CodeWhale packages codewhale / codewhale-tui versions = 0.8.41 and 0.8.64 contain a remote code execution vulnerability in the rlm eval tool. The tool's approval requirement returns ApprovalRequirement::Auto, which the engine treats as 'never prompt,' causing arbitrary model-supplied Python code ...

How MCP Servers Can Expose Enterprise Secrets

MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. As more organizations adopt AI agents into their systems, that exposure can silently become a major gap in M...

vLLM: Completion prompt lists fan out into unbounded engine requests

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

CVE-2026-21832

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

CVE-2026-21832

HCL AION is identified as affected by CVE-2026-21832, where indirect prompt injection can lead to HTML injection in rendered output. The injected markup may be displayed to users, potentially causing unintended behavior or security impact under certain conditions. The provided documents do not sp...

CVE-2026-21832 HCL AION is affected by multiple security vulnerabilities.

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

EUVD-2026-57929

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

CVE-2026-73487

Flowise before 3.1.3 contains a regex-based Python code validator bypass in CSV and Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.readjson to exfiltrate datasets, perform SSRF...

CVE-2026-73487 Flowise before 3.1.3 Prompt Injection RCE via CSV Agent

Flowise before 3.1.3 contains a regex-based Python code validator bypass in CSV and Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.readjson to exfiltrate datasets, perform SSRF...

EUVD-2026-57803

Flowise before 3.1.3 contains a regex-based Python code validator bypass in CSV and Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.readjson to exfiltrate datasets, perform SSRF...

CVE-2026-73487 Flowise before 3.1.3 Prompt Injection RCE via CSV Agent

Flowise before 3.1.3 contains a regex-based Python code validator bypass in CSV and Airtable Agent nodes that allows unauthenticated attackers to inject malicious code via prompt injection. Attackers can exploit unblocked pandas functions like pd.readjson to exfiltrate datasets, perform SSRF...

CVE-2026-73487

Flowise prior to version 3.1.3 is affected by a vulnerability in the CSV and Airtable Agent nodes where a regex-based Python code validator bypass enables unauthenticated prompt injection. This can allow an attacker to inject and execute code, exfiltrate datasets via unblocked pandas functions (e...

PT-2026-71495

HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions...

OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers'...

EUVD-2026-56896

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...

CVE-2026-73032

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability: an unsanitized LLM response passed to window.eval() in views.ts allows arbitrary JavaScript execution in Zotero's chrome-privileged context. Attackers can exploit prompt injection in PDFs, MITM interception of API requests...

CVE-2026-73032 PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...

CVE-2026-73032 PapersGPT for Zotero 0.6.1 RCE via Unsanitized LLM Response eval()

PapersGPT for Zotero 0.6.1 contains a remote code execution vulnerability that allows attackers to execute arbitrary JavaScript by returning malicious code from an LLM endpoint that is passed unsanitized to window.eval in views.ts. Attackers can exploit this through prompt injection in PDFs, MITM...