The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the analysis of external technical artifacts, such as Kubernetes manifests and deployment definitions, to generate documentation. This establishes a surface for indirect prompt injection, where malicious instructions could be embedded in the analyzed manifests. However, the risk is minimal as the skill's capabilities are restricted to documentation and diagram generation, lacking any high-privilege functions like system command execution or network exfiltration. No explicit boundary markers or sanitization steps are defined for these inputs.

c4-container