The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites to analyze search rankings, which presents a surface for indirect prompt injection if those websites contain malicious content designed to influence the AI.
Ingestion points: Search result pages from amazon.com and index verification data from google.com (retrieved via web_fetch).
Boundary markers: The prompt instructions do not specify clear delimiters or "ignore" instructions for the data retrieved from external sources.
Capability inventory: The skill primarily generates strategic recommendations and analysis reports; no dangerous system commands, file-writing, or administrative operations were identified.
Sanitization: The instructions do not define specific sanitization or validation logic for the fetched search result data.
[DATA_EXFILTRATION]: The skill performs network operations using web_fetch to retrieve ranking snapshots from amazon.com and performs index validation using Google Search. These network requests are directed to well-known services and are standard for the skill's stated purpose of keyword ranking analysis.

amazon-rank-tracker