news-signal-outreach

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (news articles, LinkedIn posts) to automate workflows, creating a surface for indirect prompt injection.
  • Ingestion points: External news items provided via URLs or raw text in SKILL.md (Step 1).
  • Boundary markers: No clear delimiters or instructions are present to ensure the agent ignores malicious instructions embedded within the fetched content.
  • Capability inventory: The skill has access to tools for web searching, contact retrieval, and outreach tool integration (e.g., Smartlead).
  • Sanitization: The skill does not define any content validation or sanitization steps for data retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 09:40 AM
Security Audit — agent-trust-hub — news-signal-outreach