agentkit-seo
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill directs the agent to fetch and inspect public material from URLs provided during the request, creating an attack surface for indirect prompt injection. External content could potentially contain instructions designed to manipulate the agent's behavior.
- Ingestion points: Fetching or inspecting public material as described in the Intake workflow section of SKILL.md.
- Boundary markers: The skill does not provide instructions for using delimiters or boundary markers to separate external data from system instructions.
- Capability inventory: The skill orchestrates tasks and routes them to specialized SEO modules (LinkedIn, GitHub, CV, etc.).
- Sanitization: There are no specified sanitization or validation procedures for the content retrieved from public URLs.
Audit Metadata