paid-landing-page-audit
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted third-party content from landing pages (URLs, HTML, or text), creating a surface for indirect prompt injection where instructions hidden on a website could attempt to override the agent's behavior.
- Ingestion points: Untrusted data enters the agent's context through live URLs or pasted HTML/content during the audit interview process defined in SKILL.md.
- Boundary markers: The skill provides defensive instructions in the 'Untrusted Page Content' section of SKILL.md, explicitly telling the agent to treat page content as data, ignore embedded directives, and avoid submitting forms or entering credentials.
- Capability inventory: The skill utilizes web fetching and rendering tools to perform audits but is restricted to naming and ranking fixes rather than executing code or implementing changes.
- Sanitization: The instructions emphasize a logical separation between the audit instructions and the data being analyzed, though no automated sanitization of the fetched content is described.
Audit Metadata