The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill. The skill operates as a set of logical instructions for the AI to transform user input into structured text output (task tables).
[SAFE]: The reference file references/edge-case-checklist.md contains strings like ../../etc/passwd and '; DROP TABLE. These are correctly placed within a developer's checklist for identifying potential software vulnerabilities during the planning phase and do not constitute an injection or exfiltration attempt within the skill itself.
[SAFE]: The skill does not request access to any tools or external resources, minimizing the attack surface for indirect prompt injection or data exposure.

task-decomposer