prospect-panel-simulator
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: The skill fetches untrusted data from remote URLs using the
WebFetchtool during 'Step 1 — Take in the artifact' to simulate reactions to landing pages or pricing pages. - Boundary markers: The instructions lack defined boundary markers or specific directives for the agent to ignore instructions embedded within the processed artifacts.
- Capability inventory: The skill is configured with powerful tools including
Bash,Write, andAgent, which increases the potential impact if the agent follows malicious instructions contained in an ingested artifact. - Sanitization: No sanitization or validation of the fetched content is performed before the agent processes it to generate the prospect simulation.
Audit Metadata