The Agent Skills Directory

[SAFE]: A comprehensive analysis of all 10 threat categories revealed no malicious patterns or security risks. The skill uses a well-defined instructional design workflow to transform content into visual summaries.
[COMMAND_EXECUTION]: The skill employs basic Bash commands like test -f to check for local configuration files within established project directories. These operations are limited to environment setup and do not involve executing untrusted input.
[PROMPT_INJECTION]: The skill processes external content to generate image creation prompts. It implements strong mitigating controls by instructing the agent to preserve all source data verbatim and avoid summarization or rephrasing, which limits the potential for indirect prompt injection to influence the generation process.
[DATA_EXFILTRATION]: No network operations or unauthorized file reads were detected. The skill operates within the local project context and delegates image generation to external tools through standard agent capabilities.

canghe-infographic