schema-validator
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse external data including 'page source', 'URL content', and 'JSON-LD snippets' (SKILL.md, Workflow section). This creates an attack surface where an attacker could embed malicious instructions in a web page's HTML or schema comments to influence the agent when a user attempts to validate that page.
- Ingestion points: Processes page source, URLs, and code snippets in the Workflow steps (SKILL.md).
- Boundary markers: The skill uses a structured output format ('Schema Validation Report') which helps maintain context, but it lacks explicit instructions to ignore embedded natural language commands within the data being validated.
- Capability inventory: The skill is primarily diagnostic and does not appear to execute shell commands, perform file writes, or initiate arbitrary network requests beyond the initial URL collection.
- Sanitization: There is no explicit mention of sanitizing or escaping the content of the page source before analysis.
Audit Metadata