The Agent Skills Directory

[SAFE]: The skill does not contain any obfuscated code, base64 strings, or hidden command execution patterns.- [SAFE]: All external references and dependencies point to the official infrastructure of the skill author at pangolinfo.com.- [PROMPT_INJECTION]: The skill provides an attack surface for Indirect Prompt Injection because it fetches and processes untrusted data from Amazon product pages, including titles, descriptions, and reviews. 1. Ingestion points: Data enters the context through tools like get_amazon_product and get_amazon_reviews in SKILL.md. 2. Boundary markers: The instructions lack specific delimiters or 'ignore' directives for the scraped content. 3. Capability inventory: The skill can summarize data and call multiple scraping tools. 4. Sanitization: No sanitization or filtering of the scraped content is implemented within the skill instructions.

pangolinfo-amazon-scraper