The Agent Skills Directory

[Prompt Injection] (SAFE): The instructions are purely functional and do not attempt to bypass safety constraints or override agent behavior.
[Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive paths, or network exfiltration patterns were detected.
[Remote Code Execution] (SAFE): The skill does not perform any remote code execution or script downloads.
[Indirect Prompt Injection] (LOW): While the skill ingests data from local files (README.md, docs), it lacks dangerous capabilities like network access or code execution, minimizing the risk of exploitation. Evidence:
Ingestion points: Reads README.md, docs, and code files (Workflow step 1).
Boundary markers: Absent.
Capability inventory: No subprocesses, network, or file-write capabilities detected.
Sanitization: Absent.

concise-planning