The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses curl to fetch data from https://hormuzstraitmonitor.com/api/dashboard. While this is central to its stated purpose, the domain is not in the trusted or well-known service categories.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from an external API, which could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: SKILL.md retrieves content from the external dashboard API via curl.
Boundary markers: Absent; the instructions do not provide specific delimiters or warnings to the agent to disregard potential instructions embedded in the API response.
Capability inventory: The skill is restricted to reading data and formatting it for the user; it does not possess file-writing or system-level command execution capabilities beyond the initial curl fetch.
Sanitization: Absent; there is no mention of filtering or validating the API content before the agent processes and presents it to the user.

hormuz-strait