seo-audit

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts to perform core functions including data fetching, authentication checks, and reporting. Evidence: references to scripts/fetch_page.py, scripts/google_auth.py, scripts/backlinks_auth.py, scripts/drift_history.py, and scripts/google_report.py in SKILL.md.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting data from external URLs.
  • Ingestion points: The skill fetches the homepage and crawls up to 500 pages using scripts/fetch_page.py.
  • Boundary markers: Absent; there are no explicit instructions to ignore embedded commands or use delimiters for the fetched HTML.
  • Capability inventory: The skill can execute local Python scripts and delegate tasks to numerous specialized sub-agents.
  • Sanitization: The instructions do not specify any validation or sanitization for the ingested web content.
  • [EXTERNAL_DOWNLOADS]: The skill performs automated crawling and fetching of external website content for audit purposes. Evidence: The audit process involves fetching page HTML from user-provided URLs via scripts/fetch_page.py.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:11 PM