affiliate-recruitment-outreach
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted content from prospect websites to personalize outreach.
- Ingestion points: Untrusted data is ingested from prospect websites and external discovery tools in
SKILL.md(Workflow steps 2 and 4). - Boundary markers: Absent; there are no specific instructions to wrap or delimit external data within the prompt instructions.
- Capability inventory: The skill's actions are restricted to drafting outreach messages, generating sequence tables, and tracking plans. No administrative commands or system-level modifications are invoked.
- Sanitization: No automated sanitization or filtering of external content is specified before interpolation into message drafts, though human review is implied via the quality gate.
- [SAFE]: No malicious patterns or security risks were identified beyond the inherent data processing surface. The skill provides robust guidance on brand safety, manual verification, and adherence to international outreach regulations, such as CAN-SPAM and GDPR. It explicitly discourages the use of risky automation tools.
Audit Metadata