speckit-git-remote
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard
gitcommands (git rev-parseandgit config) to detect if a directory is a Git repository and to retrieve the remote origin URL. These commands are typical for development tools and are restricted to local environment discovery.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads the Git remote URL, which is a source of external data from the local environment. This presents a potential surface for indirect prompt injection if a repository's configuration is maliciously crafted to influence the agent's behavior. However, the risk is minimal as the instructions constrain the agent's task to simple pattern extraction (owner and repository name).\n - Ingestion points: The output of
git config --get remote.origin.urlis processed by the agent in SKILL.md.\n - Boundary markers: No explicit delimiters or boundary markers are used to separate the external data from the system instructions.\n
- Capability inventory: The skill is limited to shell command execution for reading local Git configuration.\n
- Sanitization: The instructions include a manual check to ensure the URL points specifically to 'github.com' before reporting it, providing a basic form of validation.
Audit Metadata