competitor-research
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface because it processes untrusted data scraped from the web and Facebook.
- Ingestion points: Competitor data, descriptions, and metadata are ingested from web searches and the Apify Facebook Pages Scraper (SKILL.md).
- Boundary markers: The skill includes a dedicated safety block that explicitly labels scraped content as untrusted and directs the agent to ignore any instructions found within it.
- Capability inventory: The skill utilizes web search tools, subagent invocation, and network requests to Apify and Airtable APIs (SKILL.md).
- Sanitization: The instructions require the agent to quote and stop if scraped content appears to address the agent directly, preventing autonomous execution of embedded commands.
- [EXTERNAL_DOWNLOADS]: The skill interacts with external APIs to fulfill its intended purpose.
- Fetches data using Apify's Facebook Pages Scraper and populates records in Airtable. Both are well-known technology services and are used here for legitimate functionality.
Audit Metadata