Prompt Injection
231 entries
Every Prompt Injection entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
Gemini CLI: Remote Code Execution via workspace trust and tool allowlisting bypasses
# Summary Gemini CLI (`@google/gemini-cli`) and the `run-gemini-cli` GitHub Action are being updated to harden workspace trust and tool allowlisting, in particular when used in untrusted environments...
k8sGPT has Prompt Injection through its k8sGPT-Operator
### Summary In the auto-remediation pipeline, `object_to_execution.go` was deserializing the AI-generated YAML directly into a Deployment object, but there was lack of validation from the original Dep...
CVE-2026-41318: AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatti
AnythingLLM is an application that turns pieces of content into context that any LLM can use as references during chatting. Prior to version 1.12.1, AnythingLLM's in-chat markdown renderer has an unsa...
CVE-2026-41265: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific fl
Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the Airtable_Agents class. The issue results...
CVE-2026-41264: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific fl
Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the CSV_Agents class. The issue results from...
Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability
## Abstract Trend Micro's Zero Day Initiative has identified a vulnerability affecting FlowiseAI Flowise. ## Vulnerability Details - **Version tested:** 3.0.13 - **Installer file:** https://github....
Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace
Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its u...
Google Patches Antigravity IDE Flaw Enabling Prompt Injection Code Execution
Cybersecurity researchers have discovered a vulnerability in Google's agentic integrated development environment (IDE), Antigravity, that could be exploited to achieve code execution. The flaw, since...
Flowise: Airtable_Agent Code Injection Remote Code Execution Vulnerability
ZDI-CAN-29412: FlowiseAI Flowise Airtable_Agent Code Injection Remote Code Execution Vulnerability Trend Micro's Zero Day Initiative has identified a vulnerability affecting the following products: F...
Flowise: APIChain Prompt Injection SSRF in GET/POST API Chains
### Summary A Server-Side Request Forgery (SSRF) vulnerability exists in FlowiseAI's POST/GET API Chain components that allows unauthenticated attackers to force the server to make arbitrary HTTP requ...
Flowise: Remote code execution vulnerability in AirtableAgent.ts caused by lack of input verification when using `Pandas`.
## Description ### Summary “AirtableAgent” is an agent function provided by FlowiseAI that retrieves search results by accessing private datasets from airtable.com. “AirtableAgent” uses Python, alon...
PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands
## Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves `execute_command` for any command (e.g., `ls -la...
PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)
Summary The memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run() with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py lines...
PraisonAI Vulnerable to OS Command Injection
The `execute_command` function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbit...
PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code
### Summary `execute_code()` in `praisonai-agents` runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a `str` subclass with an overridden `startswith()...
Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories
The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt inj...
SSRF in @aborruso/ckan-mcp-server via base_url allows access to internal networks
## Summary The `@aborruso/ckan-mcp-server` MCP server provides tools including `ckan_package_search` and `sparql_query` that accept a `base_url` parameter, making HTTP requests to arbitrary endpoints...
Langflow has Remote Code Execution in CSV Agent
# 1. Summary The CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can execute...
CAI find_file Agent Tool has Command Injection Vulnerability Through Argument Injection
## Summary The CAI (Cybersecurity AI) framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via `subprocess....
LangChain serialization injection vulnerability enables secret extraction
## Context A serialization injection vulnerability exists in LangChain JS's `toJSON()` method (and subsequently when string-ifying objects using `JSON.stringify()`. The method did not escape objects...
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
## Summary A serialization injection vulnerability exists in LangChain's `dumps()` and `dumpd()` functions. The functions do not escape dictionaries with `'lc'` keys when serializing free-form dictio...
LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions
A vulnerability in the `default_jsonalyzer` function of the `JSONalyzeQueryEngine` in the run-llama/llama_index repository allows for SQL injection via prompt injection. This can lead to arbitrary fil...
PandasAI interactive prompt function Remote Code Execution (RCE)
PandasAI uses an interactive prompt function that is vulnerable to prompt injection and run arbitrary Python code that can lead to Remote Code Execution (RCE) instead of the intended explanation of th...
Flowise OverrideConfig security vulnerability
### Impact Flowise allows developers to inject configuration into the Chainflow during execution through the `overrideConfig` option. This is supported in both the frontend web integration and the bac...
PYSEC-2024-115
A vulnerability in the GraphCypherQAChain class of langchain-ai/langchain-community version 0.2.5 allows for SQL injection through prompt injection. This vulnerability can lead to unauthorized data ma...