The Agent Skills Directory

[No Code] (SAFE): The skill consists entirely of a markdown configuration file with no accompanying scripts (.py, .js, .sh) or binary executables, which eliminates the risk of direct remote code execution or persistence mechanisms.
[Prompt Injection] (SAFE): No instructions designed to bypass agent safety filters or override system instructions were found. The metadata and purpose align with legitimate developer assistance.
[Indirect Prompt Injection] (SAFE): While the skill interacts with untrusted project data through Read and Grep tools, there is no evidence of complex orchestration or unsafe interpolation that would lead to malicious exploitation.
Ingestion points: Reads files via standard Read, Grep, and Glob tools.
Boundary markers: None explicitly defined.
Capability inventory: Limited to filesystem operations (Write, Edit) without shell execution or network access.
Sanitization: Implicitly handled by the agent's core logic as no custom logic is provided.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or instructions to access sensitive paths (like .ssh or .aws) were detected. The skill lacks network tools (curl, wget) required for exfiltration.

a11y-analyzer