agentkit-seo
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data, such as public URLs and user-supplied assets (LinkedIn profiles, CVs), creating an ingestion surface for potential indirect prompt injection attacks.\n
- Ingestion points: The routing and intake workflows in
SKILL.mdspecify fetching public material and inspecting user-supplied exports or local files.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in
SKILL.mdto protect against instructions in external content.\n - Capability inventory:
SKILL.mdorchestrates multiple platform-specific modules that process file and web data.\n - Sanitization: There is no evidence of content sanitization or validation for ingested external data described in
SKILL.md.\n- [EXTERNAL_DOWNLOADS]: The skill includes links to an external GitHub repository and project documentation.\n - Evidence: References to
https://github.com/agentkit-seo/agentkit-seoandhttps://agentkit-seo.github.io/are listed for user information inSKILL.md.
Audit Metadata