event-prospecting-pipeline
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external sources.\n
- Ingestion points: Scraped data from Luma event pages, conference websites, and attendee bios (documented in
SKILL.mdStep 1).\n - Boundary markers: The workflow lacks explicit boundary markers to isolate the untrusted external data from the agent's instructional context.\n
- Capability inventory: The skill possesses the capability to perform automated outreach and email operations using the
agentmailandsetup-outreach-campaignskills (referenced inSKILL.mdStep 7).\n - Sanitization: No sanitization or validation mechanisms are identified for the retrieved external text before it is used for lead qualification or outreach generation.
Audit Metadata