lead-discovery

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes untrusted data from external websites and web search results to build a shared context for downstream actions.
  • Ingestion points: The skill uses WebFetch to scrape user-provided URLs and WebSearch to research competitors and ecosystems in SKILL.md (Phases 1 and 2).
  • Boundary markers: There are no explicit instructions or delimiters (such as XML tags or clear 'ignore instructions' directives) to prevent the agent from following malicious instructions found within the scraped content.
  • Capability inventory: The skill is granted access to high-privilege tools including Bash, Write, Edit, WebFetch, and WebSearch across all scripts.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation procedures for the external content before it is interpolated into the shared context object.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:34 PM
Security Audit — agent-trust-hub — lead-discovery