The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository's file system, including git history, logs, and README files, to perform its analysis. * Ingestion points: Reads local repository files such as README, AGENTS.md, manifests, and command outputs from git log and git status. * Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the files being analyzed. * Capability inventory: The skill utilizes local CLI tools including git and rg for data retrieval. It lacks capabilities to write to the filesystem, perform network operations, or execute code. * Sanitization: There is no evidence of sanitization or filtering applied to the content read from the repository before processing.
[COMMAND_EXECUTION]: The skill instructs the agent to execute local command-line tools to gather repository statistics and history. * Evidence: Uses git log --stat, git blame, git status --short, and rg (ripgrep) to collect data for scoring targets. These are used for read-only inspection as defined in the skill's workflow.

targetify