event-prospecting-pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources such as attendee bios, conference websites, and web search results.
- Ingestion points: Step 1 (Find Attendees / Speakers) and Step 2 (Research & Enrich) in
SKILL.mdinvolve fetching data from external URLs and attendee-provided bios. - Boundary markers: The instructions do not define boundary markers or explicit instructions to ignore potentially malicious embedded content within the ingested data.
- Capability inventory: The skill possesses capabilities including web searching, contact information retrieval (emails), and the execution of outreach campaigns via
setup-outreach-campaignoragentmail(SKILL.md). - Sanitization: There are no specified sanitization or escaping procedures for external content before it is utilized in subsequent steps like lead qualification or outreach personalization.
Audit Metadata