idea-generation
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data to inform its brainstorming process. While this represents a vulnerability surface, the risk is mitigated by the lack of execution-based tools available to the skill.\n
- Ingestion points: The skill reads project context from
.agents/youtube-context.mdand processes user-supplied inputs regarding niche, audience, and trending topics.\n - Boundary markers: There are no boundary markers, XML tags, or specific instructions to ignore embedded commands within the ingested content.\n
- Capability inventory: The skill does not invoke any scripts, subprocesses, network tools, or filesystem-writing capabilities.\n
- Sanitization: No sanitization, filtering, or validation logic is applied to the data retrieved from external files or user inputs.
Audit Metadata