dayu-upload

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands via the sau CLI tool. It provides example scripts (scripts/examples/dayu_cli_template.py, scripts/examples/dayu_commands.sh, scripts/examples/dayu_commands.ps1) that use subprocess.run and shell execution to automate social media tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted user data to construct CLI commands.
  • Ingestion points: User-provided strings for titles (--title), descriptions (--desc), and file paths (--file, --content-file) as specified in SKILL.md.
  • Boundary markers: The instructions recommend using double quotes for string arguments in the command line (e.g., --title "用户的视频标题").
  • Capability inventory: The skill can execute local CLI tools and interact with the file system via the sau command set.
  • Sanitization: The skill relies on the standard argument parsing of the sau tool and Python's subprocess.run (using lists of arguments) to prevent command injection, though no explicit pre-sanitization of the content itself is described.
  • [EXTERNAL_DOWNLOADS]: The skill instructions note that Markdown rendering requires Node.js 22+ and the execution of sau article setup. While this implies external dependencies, they are presented as standard requirements for the tool's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 04:53 PM