Back to skill

Security audit

Anyparse Skill

Security checks across malware telemetry and agentic risk

Overview

This skill uploads a user-chosen document to a user-configured AnyParse API for parsing, which matches its stated purpose but requires privacy-aware use.

Install only if you trust the AnyParse API endpoint you configure and are comfortable sending selected documents to it. Prefer a private or HTTPS endpoint, avoid using it on sensitive documents unless the service meets your data-handling requirements, and consider pinning requests before installation for reproducibility.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tainted flow: 'url' from os.environ.get (line 91, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Content
'file': open(f"{filepath}",'rb')
        }

        res = rq.post(url, files = files, data = args, headers = headers)
        return res.json()    
    except Exception as e:
        return {
Confidence
94% confidence
Finding
res = rq.post(url, files = files, data = args, headers = headers)

Tainted flow: 'files' from open (line 99, file read) → requests.post (network output)

High
Category
Data Flow
Content
'file': open(f"{filepath}",'rb')
        }

        res = rq.post(url, files = files, data = args, headers = headers)
        return res.json()    
    except Exception as e:
        return {
Confidence
89% confidence
Finding
res = rq.post(url, files = files, data = args, headers = headers)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill requires environment access, local file input, and network access to function, but it does not explicitly declare permissions despite those capabilities being evident in the metadata and usage instructions. Missing permission declarations reduce transparency and can cause users or orchestration systems to underestimate that the skill reads local files and transmits their contents to an external service.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
This skill parses user-supplied local documents by sending them to the configured AnyParse API, which means document contents and related metadata leave the local environment. The documentation mentions the API but does not provide a prominent, plain-language warning that sensitive file contents and metadata are transmitted externally during parsing, creating a meaningful privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The script uploads local file contents to an external API but provides no in-code warning, disclosure, or privacy guardrails around that transfer. For a document-parsing skill, users may not realize sensitive files are leaving the local environment, increasing privacy and compliance risk.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
Confidence
94% confidence
Finding
requests

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
88% confidence
Finding
requests

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.