The Agent Skills Directory

[SAFE]: The skill defines a functional workflow for planning and issue management without any detected malicious patterns or obfuscation.
[DATA_EXFILTRATION]: The skill implements a safety boundary by restricting all issue and pull request operations to repositories owned by 'jim60105'. This prevents the agent from writing data to or exfiltrating information via unauthorized repositories.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection during its research phase. 1. Ingestion points: Codebase content, git logs, and GitHub issue/comment threads. 2. Boundary markers: The skill does not provide instructions to ignore embedded commands in the researched data. 3. Capability inventory: Uses git commands and a tool for writing GitHub issues. 4. Sanitization: No specific filtering of retrieved content is defined.

create-plan