market-competitors
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions call for the execution of a local Python script (
scripts/competitor_scanner.py) to automate data collection from competitor URLs. - [EXTERNAL_DOWNLOADS]: The skill retrieves public content from external competitor websites via
WebFetchto populate comparison matrices and SWOT analyses. - [PROMPT_INJECTION]: The skill processes untrusted web data during its research phase, which is a surface for indirect prompt injection.
- Ingestion points: Data retrieved from competitor homepages, pricing pages, and blogs (Phase 1.3, Phase 2).
- Boundary markers: No explicit delimiters are specified to isolate fetched content within the instructions.
- Capability inventory: The skill writes the generated intelligence report to a local file (
COMPETITOR-REPORT.md). - Sanitization: No explicit instructions for sanitizing or escaping the retrieved web content are provided.
Audit Metadata