competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to research competitors by visiting external websites and review platforms like G2 and Capterra. This creates a surface for indirect prompt injection, where malicious actors could embed instructions on those pages to manipulate the agent.
- Ingestion points: External research from competitor sites and review platforms described in SKILL.md.
- Boundary markers: No specific instructions are provided to the agent to treat external content as untrusted or to ignore embedded commands.
- Capability inventory: While the skill focuses on content, the agent platform typically provides the tools for file operations and web navigation.
- Sanitization: There are no specified steps for validating or filtering the information retrieved from external sources.
Audit Metadata