Skills
skills/nikiandr/goose-skills/programmatic-seo-spy/Gen Agent Trust Hub

programmatic-seo-spy

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from competitor websites, presenting an indirect prompt injection surface. 1. Ingestion points: Data is ingested via site-content-catalog and fetch_webpage tools. 2. Boundary markers: No explicit delimiters or ignore instructions are provided for external content. 3. Capability inventory: The agent can execute shell commands, perform web searches, and write files. 4. Sanitization: No sanitization of crawled content is specified.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts to perform core crawling and analysis functions. Evidence: The skill invokes python3 skills/site-content-catalog/scripts/catalog_site.py --url "<competitor_url>" --output json using user-supplied URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:18 PM