The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/inspect_repository.py executes system git commands to discover repository metadata. It employs secure practices including environment variable sanitization (removing GIT_CONFIG_PARAMETERS, GIT_DIR, etc. to prevent credential leakage) and non-shell subprocess execution to mitigate command injection risks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local Git repositories, such as branch names and status messages, which represent a potential attack surface. This risk is effectively mitigated by the skill's instructions, which mandate a clear distinction between factual data and agent suggestions and require explicit human-in-the-loop authorization for all destructive or state-changing actions.
[EXTERNAL_DOWNLOADS]: The SKILL.md file suggests using npx skills add to install related tools from the same author (full-stack-skills). These references align with the vendor's own ecosystem and represent standard modular expansion rather than a security threat.

git-init