event-prospecting-pipeline
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources.
- Ingestion points: External data enters the agent's context through
luma-event-attendees(Step 1),conference-speaker-scraper(Step 1), and general web search results (Step 2) as defined inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the scraped attendee bios or company research.
- Capability inventory: The agent has the capability to export data to
Google SheetsandCSV, and to perform automated outreach viaagentmailorsetup-outreach-campaign(Step 7) inSKILL.md. - Sanitization: There is no mention of sanitization or filtering logic to neutralize instructions that might be hidden in conference attendee profiles or news articles.
Audit Metadata