Competitor Monitor

Warn

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The documentation explicitly instructs users to install additional skills (afrexai-lead-scorer, afrexai-seo-writer) from an untrusted source via the clawhub package manager. These external dependencies have not been verified for safety.
  • [PROMPT_INJECTION] (MEDIUM): The skill is highly susceptible to Indirect Prompt Injection (Category 8) as its core function is to ingest and analyze untrusted external data. * Ingestion points: Competitor websites, pricing pages, job boards, and third-party review sites (G2, Capterra). * Boundary markers: None. The instructions lack delimiters or warnings to the agent to ignore instructions embedded in the external content. * Capability inventory: Primarily research and strategic reasoning. While it does not perform automated write operations in this file, the recommended 'Lead scoring' skill suggests a chain of capabilities that increases risk. * Sanitization: None specified. The agent is directed to directly monitor and analyze content from the open web without filtering.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 14, 2026, 06:02 PM