competitor-experience-audit
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit and analyze external websites, creating a surface where malicious instructions embedded in those sites could influence the agent's behavior.
- Ingestion points: The workflow in
SKILL.mdrequires the agent to "Render and view each site as a user would" to assess design and UX dimensions. - Boundary markers: The instructions do not specify the use of delimiters or clear separation between the untrusted content from external sites and the agent's internal reasoning/instructions.
- Capability inventory: The skill utilizes web browsing capabilities to fetch and render content from arbitrary URLs provided by the user.
- Sanitization: There are no explicit instructions for the agent to sanitize, filter, or ignore potential prompt injection attempts located within the HTML or rendered text of the audited websites.
Audit Metadata