affiliate-recruitment-outreach

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to visit and verify external prospect websites during the qualification phase (Step 4 in SKILL.md). These untrusted third-party sites could contain malicious instructions intended to influence the agent's drafting process.
  • Ingestion points: The agent ingests data from external URLs during the prospect verification (Step 4) and qualification (Step 2) phases.
  • Boundary markers: The skill does not provide specific instructions to use delimiters or ignore instructions found within the content of external websites.
  • Capability inventory: The agent generates structured recruitment plans and multi-touch email sequences using the information gathered from these sites.
  • Sanitization: The workflow lacks explicit steps for sanitizing or filtering data retrieved from the web before it is interpolated into the generated outreach artifact.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:17 PM
Security Audit — agent-trust-hub — affiliate-recruitment-outreach