okendo
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to create components that ingest and render external, user-generated data (Okendo reviews).
- Ingestion points: External review data (titles, bodies, and reviewer names) is fetched via
@replohq/sdkloaders and passed to client components inSKILL.md. - Boundary markers: No explicit instructions are provided to the agent to sanitize or delimit the review content to prevent it from being interpreted as instructions by downstream AI processes.
- Capability inventory: The skill focuses on UI rendering; however, if this data is subsequently processed by an LLM-based agent, the embedded text could influence behavior.
- Sanitization: Relies on standard React JSX escaping for UI rendering, but lacks specific guardrails for content processed by AI agents.
Audit Metadata