skills/emmsixx/skills/file-uploads/Gen Agent Trust Hub

file-uploads

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/upload.py) to handle file uploads. This is the primary function of the skill and is implemented securely using absolute paths and standardized argument parsing.
  • [EXTERNAL_DOWNLOADS]: The skill connects to a vendor-owned domain phobos.m6.rs to upload files. As this domain is associated with the author's infrastructure (emmsixx), it is considered a legitimate service endpoint for the skill's functionality.
  • [DATA_EXFILTRATION]: The skill sends local files to an external server. However, it includes explicit instructions preventing the upload of sensitive files (like .env, SSH keys, or credentials) unless the user explicitly requests a specific file. The script also validates that the target path is a regular file and accessible before proceeding.
  • [CREDENTIALS_UNSAFE]: The skill uses a PHOBOS_TOKEN for authentication. It correctly instructs the user to provide this via an environment variable rather than hardcoding it or passing it as a command-line argument, which is a security best practice for managing secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:50 PM
Security Audit — agent-trust-hub — file-uploads