seo-schema-markup

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from both remote and local sources, creating a surface for indirect prompt injection.
  • Ingestion points: The workflow involves fetching raw HTML from external URLs via curl and reading personal/company notes from local Obsidian vaults (specifically mentioned as folders containing .obsidian directories and .md files).
  • Boundary markers: No delimiters or specific instructions (like "treat the following as data only") are provided to separate these external inputs from the agent's core instructions.
  • Capability inventory: The skill has the ability to execute shell commands (curl), run local Python scripts (scripts/seo_audit.py), and write to the local file system by appending to SEO action logs in the Obsidian vault.
  • Sanitization: There is no evidence of sanitization or filtering logic applied to the content fetched from the web or read from local notes before it enters the agent's context.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute curl for auditing JSON-LD and microdata on live websites. It also calls a Python script (scripts/seo_audit.py) from a related skill (seo-geo-audit) to perform automated SEO sweeps.
  • [EXTERNAL_DOWNLOADS]: The agent is directed to fetch HTML source code from user-provided URLs using curl to verify structured data implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:28 AM