The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from an untrusted external website and processes it into notifications and local files.
Ingestion points: Data is fetched from the external URL https://cryptorank.io/drophunting.
Boundary markers: There are no instructions or delimiters provided to the agent to distinguish between the fetched data and its own instructions, nor is it told to ignore embedded instructions in the scraped content.
Capability inventory: The skill performs file writes to the local path ~/Documents/airdrops/ and sends external notifications using the mcp__telegram-notification__send_notification tool.
Sanitization: The skill lacks explicit sanitization or validation steps for the project names, funding amounts, and URLs scraped from the web before they are used in HTML-formatted Telegram messages.
[DATA_EXFILTRATION]: The skill performs network operations to scrape data from cryptorank.io and sends summaries to an external Telegram chat. While the domain is a well-known service and the skill includes a user-consent step before notifying, it establishes a data flow from external/local sources to an external messaging service.

airdrop-tracker