competitive-intel
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional markdown files and metadata. It does not include executable code, script files, or external software dependencies.- [PROMPT_INJECTION]: The skill's primary function is to ingest and analyze external data from competitor websites, product documentation, and public review platforms. While this processes untrusted data, it is the core purpose of a research-oriented skill.
- Ingestion points: Competitor websites, product documentation, changelogs, and third-party review sites (G2, Capterra) as specified in the research guide.
- Boundary markers: The instructions do not define specific delimiters or warnings for the agent when processing external content.
- Capability inventory: The skill assumes the agent has web browsing and data synthesis capabilities to generate research reports.
- Sanitization: No explicit content filtering or sanitization steps are defined for the external data sources.- [EXTERNAL_DOWNLOADS]: The guide references several external market research and technical analysis services (e.g., BuiltWith, SEMrush, Ahrefs, Lighthouse). These are identified as informational resources and tools for the agent to consult, not as remote scripts to be downloaded and executed.
Audit Metadata