The Agent Skills Directory

[SAFE]: The skill serves a legitimate purpose of repository scaffolding, helping to standardize how AI agents interact with a specific codebase's ticketing and documentation systems.- [COMMAND_EXECUTION]: The skill utilizes standard developer tools, specifically git and the GitHub CLI (gh). These tools are used for their intended purpose: identifying repository remotes and managing issues. There is no evidence of arbitrary or dangerous command execution.- [DATA_EXFILTRATION]: Analysis shows the skill reads local configuration files such as .git/config and CLAUDE.md. This is done to derive project context for local setup. No network operations were found that would transmit sensitive local data to external or unknown servers.- [PROMPT_INJECTION]: While the skill reads untrusted data from the repository being configured (which is a surface for indirect prompt injection), the process is highly structured and requires explicit user confirmation for all changes, which serves as a primary defense mechanism.

setup-formsg-ai-skills