leadership-change-outreach
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Apollo API and LinkedIn posts) and interpolates this content into prompts for the
email-draftingcapability. This creates a surface for indirect prompt injection if an attacker-controlled profile contains hidden instructions. - Ingestion points: Data is fetched from the Apollo API (
people/match) in Step 1 and potentially from a LinkedIn scraper (linkedin-profile-post-scraper) in Step 3. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when passing external content to the drafting model.
- Capability inventory: The skill utilizes
apollo-lead-finder,email-drafting, and local file writing for campaign results. - Sanitization: No explicit sanitization or filtering of external string content is defined before the interpolation into outreach drafts.
Audit Metadata