video-cover-packager
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script,
scripts/add-title.py, via the shell to perform image processing. The command includes arguments such as--titleand--imagethat are populated with data derived from user-provided materials and agent-generated content. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of video scripts, transcripts, and outlines to generate content packages.
- Ingestion points: User-provided video materials specified in Step 1 of
SKILL.md(scripts, transcripts, audio, video). - Boundary markers: None observed; the instructions do not specify delimiters or safety warnings for the input content.
- Capability inventory: The skill has the capability to execute shell commands (
python3 scripts/add-title.py) as described inSKILL.md(Step 8). - Sanitization: There are no explicit instructions for sanitizing or escaping the content before it is processed or passed to the shell script.
- [DYNAMIC_EXECUTION]: The skill uses runtime-generated shell commands to invoke a Python script for image synthesis. While the script itself uses standard libraries like Pillow, the method of execution involves constructing command-line strings at runtime.
Audit Metadata