baijiahao-upload
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
sau(social-auto-upload) CLI tool to perform actions like logging in, checking account status, and uploading videos. These commands are executed directly in the shell environment as documented inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as video titles and descriptions which are passed as arguments to shell commands.
- Ingestion points: User-provided video metadata (titles, descriptions, tags) defined in
SKILL.md. - Boundary markers: Absent; there are no specified delimiters for the metadata arguments in
SKILL.md. - Capability inventory: Execution of shell commands via the
sautool as seen inSKILL.md. - Sanitization: Absent; no explicit sanitization or validation of user-provided strings is mentioned before execution.
Audit Metadata