seo-content-collection-page

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites to perform SEO audits and competitor benchmarking. This creates a surface for indirect prompt injection where malicious instructions embedded in a website's HTML could influence the agent's behavior.
  • Ingestion points: External website HTML content fetched via curl in Phase 2 and competitor URLs in Phase 3.
  • Boundary markers: The instructions do not define explicit boundary markers or "ignore" delimiters for the content fetched from external URLs.
  • Capability inventory: The skill has capabilities to execute shell commands (curl, python3), write to local files (Obsidian vault), and interact with APIs (Google Search Console).
  • Sanitization: There are no explicit instructions for sanitizing or escaping the HTML/text content retrieved from the web before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands as part of its auditing process. This includes using curl to fetch raw HTML and python3 to run local scripts such as seo_audit.py, section_audit.py, and page_benchmark.py located in the skills/ directory structure.
  • [DATA_EXFILTRATION]: The skill integrates with a local knowledge base (Obsidian vault) and requires access to Google Search Console (GSC) data. While these are legitimate features for an SEO tool, they involve processing sensitive business data that could be targeted if the agent's execution is compromised via indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:28 AM