text-over-footage
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied text strings to create overlays for video content using the
edit-videotool. This creates a potential surface where malicious instructions hidden in the input text could be interpreted by the agent during the generation process. - Ingestion points: User-provided premise lines and text blocks defined in the default prompt and copy guidelines (SKILL.md, agents/openai.yaml).
- Boundary markers: The instructions lack explicit delimiters or safety warnings to ignore instructions potentially embedded within the user's video text.
- Capability inventory: The skill interacts with the
edit-videoandpublish-and-analyzetools to generate and modify media files. - Sanitization: There are no instructions for sanitizing or escaping the text content before it is processed by the underlying video editing tools.
- [NO_CODE]: The skill contains no executable scripts (Python, JavaScript, shell) or binary files, consisting entirely of Markdown instructions and YAML configuration.
Audit Metadata