The Agent Skills Directory

[SAFE]: The skill provides documentation and examples for standard Frappe framework caching mechanisms including frappe.cache, @redis_cache, and frappe.lock.
[DATA_EXPOSURE]: No hardcoded credentials or sensitive file access patterns were detected. Mentions of fields like api_key in examples refer to data structures rather than actual secrets.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverified package installations were found. Code examples use standard libraries like requests for illustrative API interaction.
[PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were identified in the metadata or instructional text.
[INDIRECT_PROMPT_INJECTION]: While the skill demonstrates caching data from external APIs (references/examples.md), this is a core functionality of caching systems. The instructions include best practices such as using TTL (Time-To-Live) to mitigate stale data risks.
[DYNAMIC_EXECUTION]: The skill mentions Redis's use of pickle for serialization as a performance warning (SKILL.md). This is an accurate description of the underlying framework behavior and does not instruct the user to perform unsafe deserialization of untrusted data.

frappe-core-cache