competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill is composed strictly of documentation, instructions, and YAML-based templates. No scripts, binaries, or automated command executions are included.
- [Indirect Prompt Injection] (SAFE): The skill defines a data ingestion surface (reading local context files and external reviews). Evidence Chain: 1. Ingestion points: .claude/product-marketing-context.md and web-based competitor reviews. 2. Boundary markers: Absent. 3. Capability inventory: None (no code or system-altering tools present). 4. Sanitization: Absent. This is considered safe as it aligns with the intended research-driven use case.
Audit Metadata