cold-outreach-sequence

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external data.
  • Ingestion points: Untrusted data is retrieved from the web via web_search tool calls for company news, LinkedIn activity, and stage signals.
  • Boundary markers: Absent. There are no explicit instructions or delimiters used to separate search results from the system's own instructions.
  • Capability inventory: The skill uses the retrieved data to generate text for outreach sequences and performs further tool calls.
  • Sanitization: None detected. The skill does not describe any validation or filtering logic for data returned from web searches before it is incorporated into message templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 12:16 AM