seo-keyword-analysis
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data fetched from the internet.
- Ingestion points: In SKILL.md, the Match and Exceed Principle instructs the agent to analyze the top 10 search results using the webfetch tool.
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate untrusted external content or to prevent the agent from following instructions embedded in that content.
- Capability inventory: According to SKILL.md, the agent is allowed to use webfetch and various Google Search Console tools.
- Sanitization: There is no evidence of sanitization or filtering applied to the content retrieved from external sites before it is analyzed by the agent.
Audit Metadata