competitive-platform-analysis
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external, untrusted sources which could contain malicious instructions or misleading content.
- Ingestion points: The agent is directed to mine information from competitor websites, LinkedIn, and various portfolio/review platforms as described in the 'Data sources' section.
- Boundary markers: The instructions explicitly advise the agent to 'verify claims across at least two sources' and 'Carry an adversarial-verification discipline into every profile,' which serves as a prompt-based control against potentially malicious or deceptive input.
- Capability inventory: The task necessitates the use of web browsing capabilities to access the external data sources mentioned (e.g., Clutch.co, Dribbble, Behance).
- Sanitization: The skill lacks technical sanitization requirements for the content retrieved from external domains, relying instead on manual verification steps.
Audit Metadata