seo-platform-detect
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script (
detect-platform.mjs) using theBashtool. The scope of execution is restricted to the plugin's internal directory via theallowed-toolsconfiguration. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection.
- Ingestion points: Analyzes
PageSnapshotfiles containing site HTML/DOM, performs network GET requests to site endpoints (e.g.,/wp-json/), and reads local project files via the--pathargument. - Boundary markers: The documentation does not indicate the use of delimiters or instructions to prevent the agent from following instructions embedded in the analyzed data.
- Capability inventory: The skill has the ability to execute shell commands and write detection profiles to JSON files on the local filesystem.
- Sanitization: There is no evidence of sanitization or filtering applied to the external site content before it is used for platform detection and relayed to subagents.
Audit Metadata