seo-technical
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data and local project documentation, creating a surface for indirect prompt injection.
- Ingestion points: Fetches website HTML content via
curlcommands and reads local files and metadata from an Obsidian vault (.mdnotes and.obsidiandirectory). - Boundary markers: No specific boundary markers or delimiters are instructed to isolate ingested external content from internal instructions.
- Capability inventory: The skill uses shell commands (
curl) and executes local Python scripts (scripts/seo_audit.py,skills/seo-internal-linking/scripts/site_crawl.py) via subprocess calls. - Sanitization: The instructions do not define specific methods for sanitizing or validating retrieved external data before processing.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and Python scripts as part of its technical SEO workflow.
- Evidence: Direct instructions for the agent to run
python3 scripts/seo_audit.pyandcurl -sLfor auditing status codes, headers, and content visibility.
Audit Metadata