seo-opportunity-finder

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local Python and Node.js scripts to perform site cataloging and competitor domain analysis. These scripts are part of referenced sub-skills within the same repository structure.
  • Evidence: Execution of python3 skills/site-content-catalog/scripts/catalog_site.py and node skills/seo-domain-analyzer/src/cli.js analyze.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from external websites.
  • Ingestion points: Content is ingested from user-provided URLs and competitor domains via site crawling and Apify scrapers.
  • Boundary markers: There are no explicit instructions or delimiters mentioned to isolate ingested content from the agent's instructions.
  • Capability inventory: The skill has the ability to execute subprocesses (Python/Node) and write files to the local file system (e.g., clients/ directory).
  • Sanitization: No sanitization or filtering logic is described to prevent malicious instructions embedded in the scraped HTML or metadata from influencing the agent's output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM