The Agent Skills Directory

[SAFE]: The skill exclusively utilizes official Cloudflare documentation and public GitHub resources within the Cloudflare organization to provide information on Cloudflare K2. References to these well-known services and trusted organizations for documentation retrieval are standard and do not indicate malicious intent.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and use data from external Cloudflare documentation pages and a specific GitHub pull request. This creates an ingestion surface for external content.
Ingestion points: The skill provides several URLs targeting developers.cloudflare.com and a specific pull request on github.com/cloudflare/cloudflare-docs in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the external content.
Capability inventory: The skill is documentation-focused and does not define any tool capabilities, subprocess calls, or file system write operations.
Sanitization: No sanitization or validation of the retrieved documentation content is implemented within the skill instructions.

k2