The Agent Skills Directory

[SAFE]: The skill is designed for project management and documentation tracking. It defines a clear directory structure and naming conventions for requests, technical specifications, and decision records. Analysis of the skill instructions and reference files reveals no malicious patterns, obfuscation, or unauthorized access attempts.
[COMMAND_EXECUTION]: The skill includes documentation for standard shell operations such as touch, find, and mv to help manage documentation files. These operations are limited to the project's docs directory and do not involve privilege escalation or remote execution.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes project documentation. Ingestion points: Reads files from docs/features/ via Read, Grep, and Glob tools. Boundary markers: No explicit markers are used to distinguish instructions from data in the documents. Capability inventory: Limited to Read, Grep, and Glob tools as per the skill definition. Sanitization: No content sanitization is implemented, which is typical for documentation-focused skills.

request-tracking