competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill involves researching and ingesting data from external sources like G2, Capterra, and competitor websites. This presents a surface for indirect prompt injection where malicious content from these sites could attempt to influence the agent's output.
- Ingestion points: External product reviews and competitor website data.
- Boundary markers: No explicit delimiters are defined to separate untrusted web data from instructions.
- Capability inventory: The skill performs text generation and reads local marketing context files.
- Sanitization: No input validation or sanitization of the external research data is described.
Audit Metadata