The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and summarize untrusted data from external sources, specifically app store titles, descriptions, and user reviews.
Ingestion points: External data enters the agent context via the Appeeky API (e.g., api.appeeky.com/v1/apps/:id/reviews).
Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard potential instructions embedded within the competitive data.
Capability inventory: The skill provides templates for reporting and includes a Bash script example that utilizes curl and jq for data processing.
Sanitization: No explicit sanitization, filtering, or escaping of the fetched external text is mentioned before it is presented to the agent for analysis.
[COMMAND_EXECUTION]: The skill provides a functional Bash script (#!/bin/bash) as an example for users to automate data retrieval. The script executes shell commands including curl for network requests and jq for parsing JSON data.
[EXTERNAL_DOWNLOADS]: The skill's instructions and provided scripts perform network operations to an external API (api.appeeky.com) to fetch market intelligence data.

competitor-tracking