cold-email-kickoff
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill initiates a workflow that involves scraping external URLs and case studies to populate business profiles and generate campaign strategies. This introduces a surface for indirect prompt injection where malicious instructions hidden on a website could influence the agent's behavior during the onboarding or strategy generation phases.
- Ingestion points: The skill explicitly mentions scraping the user's website in Step 2 and Step 4, as well as analyzing case studies to produce campaign ideas.
- Boundary markers: There are no explicit instructions or delimiters defined in this orchestrator to tell the agent to ignore or treat scraped content as untrusted data.
- Capability inventory: The skill has the capability to invoke numerous other skills including
/icp-onboarding,/campaign-strategy, and various list-building tools which may perform further network operations or file modifications. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content retrieved from external websites before it is used to synthesize the final
campaign-plan.md.
Audit Metadata