agent-sudo-mcp

v0.5.4 suspicious
6.0
Medium Risk

Authorization, delegation, provenance, and verifiable-audit engine for AI agents

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows significant credential risk and some shell risk, indicating potential misuse or malicious intent. However, there's no clear evidence of immediate harm, leading to a cautious 'suspicious' classification.

  • High credential risk
  • Potential shell activity for non-standard purposes
Per-check LLM notes
  • Network: No network calls detected, which is typical for benign packages.
  • Shell: Git commands suggest the package may be querying version control information, possibly for logging or development purposes, rather than malicious activity.
  • Obfuscation: No signs of obfuscation patterns detected.
  • Credentials: Detected patterns suggest potential credential harvesting activities.
  • Metadata: The author has only one package on PyPI, which might indicate a new or less active account, raising some suspicion but not conclusive evidence of malice.

🔬 Heuristic Checks

Outbound Network Calls

No suspicious network call patterns found

Code Obfuscation

No obfuscation patterns detected

Shell / Subprocess Execution score 10.0

Found 6 shell execution pattern(s)

  • try: completed = subprocess.run( ["git", "rev-parse", "--show-toplevel"],
  • branch_completed = subprocess.run( ["git", "rev-parse", "--abbrev-ref", "H
  • sha_completed = subprocess.run( ["git", "rev-parse", "--short",
  • ) completed = subprocess.run( argv, cwd=self.cwd, cap
  • ) completed = subprocess.run(argv, capture_output=True, text=True, check=False) r
  • f hermes: completed = subprocess.run( [hermes, "mcp", "list"], capture_output=True, t
Credential Harvesting score 5.0

Found 2 credential access pattern(s)

  • and", target="cat /etc/passwd /secret/token.json --pass=123", payload_summary
  • ) self.assertNotIn("/etc/passwd", args1[0][2]) self.assertNotIn("123", args1[0][2])
Typosquatting

No typosquatting candidates detected

Registered Email Domain

No author email provided

Suspicious Page Links

All external links appear legitimate

Git Repository History

Repository Kisyntra/Agent_Sudo appears legitimate

Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "agent-sudo contributors" appears to have only 1 package on PyPI (new or inactive account)
Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with agent-sudo-mcp
Build a simple Python application using the agent-sudo-mcp package to demonstrate its core features.