agentscope
13 published advisories.
- Registry
- PyPI
- Advisories
- 13
- Latest fix
- No fix yet
- Exploited in the wild
- None listed
13 advisories have no fixed release in any version yet. What can be done meanwhile:
General guidance from ShieldPi, not a vendor fix
- Command or code injection. Remove or disable the affected server or tool, or run it in a sandbox with no secrets in its environment.GHSA-cr24-fv3h-8cjm · GHSA-6p55-qr3j-mpgq
- Path traversal. Limit the folders it can reach at the operating-system level, such as a container or a user with access to only those folders, and keep credentials and keys outside them.GHSA-6v28-q95m-93qr · GHSA-c4cc-w454-4634 · GHSA-f4hc-q562-cc5r · GHSA-j9rw-qm5f-r8xm · GHSA-p6h7-hfj2-vmcf
- Server-side request forgery. Restrict its outbound network access to the hosts it needs, and keep internal addresses and cloud metadata endpoints out of its reach.GHSA-659x-hm75-hpv7 · GHSA-8ggf-r3vm-p3jc · GHSA-crx8-wpv6-jrj2
- Unsafe deserialization. Do not let it load files, models or data from sources you do not trust, and keep its RPC and socket ports reachable only from localhost or hosts you trust.GHSA-9w5h-67gf-xvv8
Check your projects
shieldpi agent-config checks agent and MCP packages from npm and PyPI, not agentscope. Any scanner that reads the OSV database finds it in your lockfiles, for example Google's open-source OSV-Scanner.
osv-scanner scan source -r .Or check a lockfile against ShieldMap in your browser.
Source: github.com/agentscope-ai/agentscope, named in the package metadata (not verified)
0 of the last 10 releases of agentscope were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.
- 2.0.12
- 2.0.11
- 2.0.10
- 2.0.9
- 2.0.8
- 2.0.7.post1
- 2.0.7
- 2.0.6
- 2.0.5
- 2.0.4.post1
Green: published with provenance. Grey: without.
OpenSSF Scorecard has not scored this repository.
Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.
| Advisory | Severity | Affected | Fixed in | Published |
|---|---|---|---|---|
| AgentScope vulnerable to Server-Side Request ForgeryCVE-2026-6604 | Medium | <= 1.0.18 | No fix yet | 2026-04-20 |
| AgentScope vulnerable to Server-Side Request ForgeryCVE-2026-6605 | Medium | <= 1.0.18 | No fix yet | 2026-04-20 |
| AgentScope Vulnerable to Remote Code InjectionCVE-2026-6603 | Medium | <= 1.0.18 | No fix yet | 2026-04-20 |
| AgentScope vulnerable to Server-Side Request ForgeryCVE-2026-6606 | Medium | <= 1.0.18 | No fix yet | 2026-04-20 |
| AgentScope stored cross-site scripting (XSS) vulnerabilityCVE-2024-8556 | Medium | <= 0.1.1 | No fix yet | 2025-03-20 |
| AgentScope directory traversal vulnerability in /read-examplesCVE-2024-8524 | High | <= 0.0.4 | No fix yet | 2025-03-20 |
| AgentScope Cross-Origin Resource Sharing (CORS) vulnerabilityCVE-2024-8487 | High | <= 0.0.4 | No fix yet | 2025-03-20 |
| AgentScope Deserialization VulnerabilityCVE-2024-8502 | Critical | <= 0.0.6a3 | No fix yet | 2025-03-20 |
| AgentScope path traversal vulnerabilityCVE-2024-8537 | Critical | <= 0.1.1 | No fix yet | 2025-03-20 |
| AgentScope Path Traversal in /api/fileCVE-2024-8438 | High | <= 0.0.4 | No fix yet | 2025-03-20 |
| AgentScope path traversal vulnerability in save-workflowCVE-2024-8551 | Critical | <= 0.1.1 | No fix yet | 2025-03-20 |
| AgentScope arbitrary file download vulnerability in rpc_agent_clientCVE-2024-8501 | High | <= 0.0.4 | No fix yet | 2025-03-20 |
| AgentScope uses `eval`CVE-2024-48050 | High | <= 0.1.0 | No fix yet | 2024-11-05 |
Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].