video-caption-burner
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external subtitle files and caption text, which could contain malicious instructions designed to influence the agent's behavior during the processing or quality check phase.
- Ingestion points: Source video files, subtitle files (SRT, timing data), and raw caption text inputs specified in
SKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore instructions embedded within the subtitle content.
- Capability inventory: The workflow includes analyzing video content for collisions and recommending/executing video exports.
- Sanitization: There are no requirements for sanitizing or validating the contents of the timing files or caption text.
Audit Metadata