seo-content
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines an execution flow that ingests untrusted data from external sources without implementing safeguards against indirect prompt injection.
- Ingestion points: The skill accepts a URL as an argument and utilizes the
WebFetchtool to retrieve content for analysis. - Boundary markers: The instructions do not employ delimiters or explicit instructions to the AI to ignore instructions found within the fetched content, leading to a risk of the agent following embedded commands.
- Capability inventory: The skill is configured with broad tool access, including
Bashfor command execution and file system tools likeRead,Grep, andGlob, which could be abused if an injection is successful. - Sanitization: There is no sanitization or validation logic described for the content retrieved from external URLs before it enters the agent's context.
Audit Metadata