hupu-upload
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
sau(social-auto-upload) command-line tool to interact with Hupu services, including session management and content publication. - [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection by processing untrusted user input for video metadata and incorporating it into shell commands.
- Ingestion points: User-supplied values for video titles, descriptions, and tags are ingested and used as arguments for the
sau hupu upload-videocommand. - Boundary markers: Absent; there are no specified delimiters or instructions to ignore embedded commands within the user-provided text.
- Capability inventory: The skill utilizes shell command execution to perform file and network operations via the
sauCLI. - Sanitization: Absent; the instructions do not include steps to sanitize, escape, or validate the user-provided strings before they are interpolated into the command-line execution string.
Audit Metadata