competitor-alternatives
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to perform deep research by visiting external competitor websites and third-party review platforms (e.g., G2, Capterra, TrustRadius). This ingestion of untrusted content from the open web creates a vulnerability surface for indirect prompt injection, where an attacker could place malicious instructions on those sites to influence the agent's behavior during analysis.
- Ingestion points: External research sources including competitor websites and public software review platforms.
- Boundary markers: The skill does not provide specific instructions or delimiters to isolate retrieved content or to warn the agent against executing embedded commands within research data.
- Capability inventory: The skill has access to read local configuration files (e.g., .claude/product-marketing-context.md) and generate structured marketing content.
- Sanitization: No sanitization, filtering, or validation steps are defined for the information retrieved from external websites.
Audit Metadata