The Agent Skills Directory

[Command Execution] (SAFE): The skill executes git remote get-url origin and git rev-parse --abbrev-ref HEAD to resolve repository context. These are read-only operations necessary for the primary purpose of documentation generation.
[Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from repository files to generate documentation structures.
Ingestion points: Reads README.md, file tree structure, and source code files within the repository.
Boundary markers: Absent. The skill instructions do not provide delimiters or warnings to ignore instructions embedded within the codebase being analyzed.
Capability inventory: The skill has the ability to execute git commands and read file system contents.
Sanitization: Absent. Content from the files is interpolated into prompts without explicit sanitization or validation.

wiki-architect