geo-schema

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use curl or WebFetch to retrieve HTML from target websites. While this is necessary for the skill's primary function of SEO auditing, it involves executing shell commands and network operations based on user-provided or external inputs.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external web pages.
  • Ingestion points: The skill fetches target page HTML using curl or WebFetch in Step 1 of SKILL.md to scan for structured data.
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded instructions that might be present in the fetched HTML source code or script blocks.
  • Capability inventory: The skill parses HTML, JSON-LD, Microdata, and RDFa, and generates a report file (GEO-SCHEMA-REPORT.md). It also generates JSON-LD code blocks.
  • Sanitization: Absent. The skill does not describe any sanitization, filtering, or validation of the fetched content beyond checking for valid Schema.org syntax.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 03:25 AM
Security Audit — agent-trust-hub — geo-schema