competitor-research

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the orth run utility to interact with several intelligence-gathering tools (Brand.dev, Exa, ScrapeGraph, and Fiber). These operations are restricted to the platform's approved tool ecosystem and are used for their intended research purposes.
  • [PROMPT_INJECTION]: The skill demonstrates a standard indirect prompt injection surface because it ingests and processes untrusted data from external websites.
  • Ingestion points: Data retrieved via scrapegraph (Step 3) and web search results from exa (Step 5) are incorporated into the agent's context.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the tool outputs.
  • Capability inventory: The skill possesses the ability to read local context (MEMORY.md) and execute subsequent tool calls based on processed data.
  • Sanitization: No specific sanitization or filtering logic is applied to the content scraped from competitor websites or search results before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:17 AM
Security Audit — agent-trust-hub — competitor-research