geo-platform-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting untrusted data from external websites to perform SEO audits.\n
- Ingestion points: The WebFetch tool is used to retrieve content from user-provided target URLs as described in SKILL.md.\n
- Boundary markers: The instructions lack specific delimiters or boundary markers to differentiate between the agent's internal instructions and the external content being audited.\n
- Capability inventory: The skill has access to Bash, Write, and WebFetch tools, which increases the potential impact of a successful injection attack.\n
- Sanitization: The skill does not define any sanitization, filtering, or validation steps for the external data fetched during the audit process.
Audit Metadata