The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is purely instructional, defining a workflow for auditing tasks based on evidence and Definition of Done (DoD) criteria. It does not invoke any tools, perform network operations, or access sensitive files.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting external content (task descriptions and proof artifacts). However, the risk is classified as safe because the skill does not expose any dangerous capabilities (such as code execution, file system writes, or network access) that could be triggered by instructions embedded in the analyzed data.

finished-audit