distributing-omnichannel-content
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content provided by the user, including blog posts, video transcripts, reports, or data accessed via URLs. This creates a surface for indirect prompt injection where malicious instructions hidden within the source material could attempt to hijack the agent's behavior during distillation and adaptation.
- Ingestion points: The skill explicitly requests original content in various formats or via URLs in the discovery questions and example prompts.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when processing the provided content.
- Capability inventory: The skill is capable of generating and organizing multiple files (.txt and .png) into directory structures.
- Sanitization: No sanitization or validation logic is present to filter out potential prompt injection attacks embedded in the ingested data.
Audit Metadata