The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and summarizes content from untrusted external sources.
Ingestion points: External content is pulled from Atom/RSS feeds, the GitHub API, and arbitrary web pages specified by the user or identified via the discovery skill as documented in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the LLM when processing external content for the subscription/summarize task.
Capability inventory: The skill utilizes the joelclaw CLI for management and Inngest functions for automated fetching and background processing.
Sanitization: There is no evidence of sanitization or content filtering applied to the fetched data before it is presented to the LLM for summarization.
[COMMAND_EXECUTION]: The skill uses a vendor-specific CLI tool (joelclaw) to perform administrative tasks such as listing, adding, and checking subscriptions. These commands are part of the intended local functionality.
[EXTERNAL_DOWNLOADS]: The skill retrieves data from external domains including github.com and various feed URLs. These network operations are core to the skill's purpose and target well-known services or user-defined URLs.

monitor