verify
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
ffprobeto verify video file properties such as resolution, format, and duration. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes artifacts and metadata generated in earlier workflow stages.
- Ingestion points: Data enters via 'Compose outputs' and artifact filenames used as arguments for system commands in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or instructions to ignore potential commands within the processed data.
- Capability inventory: The skill includes shell command execution capabilities via
ffprobein SKILL.md. - Sanitization: There are no documented steps for validating or sanitizing filenames or metadata before they are used in command-line arguments.
Audit Metadata