playbook-tech-on-website
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust verification workflow for identifying technologies on websites. It uses specific regex-based fingerprints and response header checks to confirm the presence of platforms like Shopify and WordPress.\n- [COMMAND_EXECUTION]: The skill references a suite of CLI tools designed for domain processing and verification. These operations are restricted to domain management and do not involve the execution of arbitrary or untrusted code.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML data from external websites. This is mitigated through a structured evidence chain: 1. Ingestion points: Website homepages via scrape-website. 2. Boundary markers: The LLM prompt utilizes explicit delimiters (e.g., VERIFIED_TECH:, EVIDENCE:). 3. Capability inventory: Scraped HTML is processed by regex, not directly executed. 4. Sanitization: Input data is filtered via regex signatures.
Audit Metadata