batch-target-search

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting and processing untrusted data from external websites.
  • Ingestion points: Untrusted data enters the agent context through the results of the WebSearch and WebFetch tools.
  • Boundary markers: There are no visible boundary markers or instructions telling the agent to ignore potential instructions embedded within the fetched web content.
  • Capability inventory: The skill possesses file system capabilities (Read, Write, Edit, Glob, Grep) and network search capabilities (WebSearch, WebFetch).
  • Sanitization: The skill does not perform sanitization, escaping, or validation on the external content before using it to generate YAML entries in search/context/target-companies.yaml.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:36 AM
Security Audit — agent-trust-hub — batch-target-search