end-screen-cta
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and does not include any code, external dependencies, or command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading external context files.
- Ingestion points: The skill reads user-provided data from
.agents/youtube-context.mdin the project root. - Boundary markers: The instructions do not define specific delimiters or "ignore" directives for the ingested content.
- Capability inventory: The skill lacks any dangerous capabilities such as file writing, network requests, or subprocess execution, rendering the ingestion surface non-exploitable.
- Sanitization: No validation or sanitization is performed on the ingested content.
Audit Metadata