video-download
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing
yt-dlpandffmpegshell commands to process media. This is the intended and primary function of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing external URLs which are passed to the
yt-dlpcommand-line utility. - Ingestion points: External video URLs provided by the user or found in conversation are passed to shell commands in
SKILL.md. - Boundary markers: The skill utilizes double quotes (e.g.,
"URL") around the input parameter to mitigate shell injection risks. - Capability inventory: The skill has the capability to execute shell commands, perform network requests to media hosting sites, and write media files to the local file system (documented in
SKILL.md). - Sanitization: The skill relies on standard shell quoting within its command templates to manage external input.
Audit Metadata