The Agent Skills Directory

[SAFE]: The skill incorporates security best practices by explicitly instructing the agent to redact sensitive user data, such as API keys and passwords, from queries before they are sent to the external documentation service.
[PROMPT_INJECTION]: The skill ingests documentation data from external sources via the query-docs tool. Ingestion point: Context7 tool output. Boundary markers: None. Capability inventory: None (the skill defines no subprocess, file-system, or unauthorized network operations). Sanitization: User secrets are redacted from outgoing queries. The surface is considered safe due to the complete lack of exploitable capabilities within the skill.
[SAFE]: No evidence of [DATA_EXFILTRATION], [REMOTE_CODE_EXECUTION], or malicious [COMMAND_EXECUTION] was found in the analyzed instructions or configuration files.

documentation-lookup