serp-markup-builder
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled Python script (
schema_lint.py) to perform pre-flight validation on structured data. The script is located within the plugin's root directory and is executed using thepython3interpreter. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of fetching and processing external web content. A malicious actor could place instructions on a webpage that the agent visits, attempting to override its behavior.
- Ingestion points: Untrusted content is ingested from external URLs via the
WebFetchtool and passed to theschema_lint.pyscript. - Boundary markers: The skill metadata includes a high-level warning to treat fetched content as untrusted data, but the implementation lacks explicit delimiters or markers to isolate this content within the prompt.
- Capability inventory: The skill allows the agent to perform network requests (
WebFetch) and execute a local Python script. - Sanitization: There are no documented steps for sanitizing or filtering the fetched HTML content before it is processed.
- [EXTERNAL_DOWNLOADS]: The skill uses
WebFetchto download remote HTML content to extract existing SEO tags and schema for optimization purposes.
Audit Metadata