seo-platform-detect
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: Processes site snapshots (SKILL.md), local project files via the
--pathflag, and remote web content through the--probeor--htmlflags. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are documented for the data ingestion phase.
- Capability inventory: The skill utilizes the
Bashtool to execute a local Node.js script (detect-platform.mjs). - Sanitization: No specific sanitization or filtering logic for the ingested content is described in the skill instructions.
Audit Metadata