competitive-landscape

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external search engine results, Google Business questions, and ranking data to synthesize a competitive landscape report.
  • Ingestion points: The agent retrieves untrusted content from the web via get_serp_results, get_google_business_questions, and get_ranked_keywords as described in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or instructions to treat external data as untrusted, which could lead the agent to follow malicious instructions embedded in search results.
  • Capability inventory: The skill uses the update_project_context tool in SKILL.md to write durable information and confirmed competitors back to the project configuration.
  • Sanitization: There is no documented mechanism for filtering or sanitizing external content before it is processed by the agent or saved to the project state.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:22 PM
Security Audit — agent-trust-hub — competitive-landscape