The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external ticketing platforms (StubHub, Ticketmaster, SeatGeek, AXS), which introduces a surface for indirect prompt injection where malicious website content could attempt to influence the agent's behavior.
Ingestion points: Scrapes and extracts information from external event pages using the webcrawl tool as described in SKILL.md.
Boundary markers: The extraction prompts do not include explicit delimiters or instructions to ignore instructions embedded within the retrieved web content.
Capability inventory: The skill can execute shell commands (npx webcrawl) and make network requests (curl) to external notification services.
Sanitization: No sanitization or content validation is performed on the scraped HTML or text before it is processed by the LLM.
[EXTERNAL_DOWNLOADS]: Uses npx webcrawl to download and execute the crawling package provided by the vendor (brainfish-ai).
[DATA_EXFILTRATION]: Transmits extracted ticket information to external notification services, including ntfy.sh and the Telegram Bot API. These are well-known services used as the destination for user-requested alerts.
[PERSISTENCE]: Recommends the use of cron in references/alerting.md to establish a recurring schedule for monitoring ticket prices, which is a standard method for session persistence in monitoring agents.
[COMMAND_EXECUTION]: Performs shell operations using npx and curl for the purpose of scraping data and sending mobile notifications.

webcrawl-ticket-watch