The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the curl utility to fetch HTML content from the postplan.dev domain and saves it to a local temporary file at /tmp/postplan.html.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from an external source, which may contain malicious instructions designed to influence the agent's behavior.
Ingestion points: External HTML content is fetched via curl and stored in /tmp/postplan.html before being read by the agent.
Boundary markers: The instructions do not define clear delimiters or provide the agent with guidance to ignore or isolate instructions potentially embedded within the fetched HTML.
Capability inventory: The skill performs shell command execution (curl) and local file system operations (writing to and reading from /tmp).
Sanitization: The skill lacks any explicit sanitization, validation, or filtering mechanisms for the data retrieved from the remote URL before it is incorporated into the agent's context.

postplan-read