The Agent Skills Directory

[SAFE]: The skill is composed of Markdown files providing UX and information design guidance. It contains no executable scripts, binaries, or automated tools.
[PROMPT_INJECTION]: The instructions provide heuristic-based design advice and do not contain any patterns designed to override agent behavior, bypass safety filters, or extract system instructions.
[DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive local file paths were found in any of the skill files.
[REMOTE_CODE_EXECUTION]: The skill does not perform any network operations, external downloads, or package installations.
[INDIRECT_PROMPT_INJECTION]: While the skill instructs the agent to audit dashboard data and screenshots, which are external ingestion surfaces, it does not include any unsafe interpolation logic or executable instructions that would process that data in a dangerous manner.
[METADATA_POISONING]: All metadata fields in the SKILL.md and openai.yaml files are descriptive and consistent with the provided design documentation.

clear-dashboards