video
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow to reverse-engineer video editing styles by analyzing external video content and social media metadata fetched via third-party tools.\n
- Ingestion points: The agent is instructed to use
watch-videoandsocial-fetchto pull transcripts, frames, and social post content from external sources.\n - Boundary markers: The instructions do not provide delimiters or specific guidelines for the agent to ignore potentially malicious instructions embedded in the analyzed transcripts or metadata.\n
- Capability inventory: The skill's primary capabilities include generating HTML/CSS (Hyperframes) and React (Remotion) code; no dangerous system-level subprocesses or exfiltration behaviors were identified in the skill files.\n
- Sanitization: No mechanisms for sanitizing or validating external content are specified in the provided instructions.
Audit Metadata