The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes command-line tools for repository management and project analysis.
Evidence: Executes git rev-parse, git fetch, git pull --rebase, and ls to manage branches and detect project manifests. These are typical development workflows for an agent operating in a code repository.
[INDIRECT_PROMPT_INJECTION]: The skill processes project files which could contain untrusted data.
Ingestion points: Reads README.md, docs/ directory, and package manifest files (e.g., package.json, pyproject.toml, Cargo.toml).
Boundary markers: Absent; there are no specific delimiters instructing the agent to ignore instructions embedded within the analyzed files.
Capability inventory: The skill has the capability to execute git commands and perform file system read/write operations.
Sanitization: No explicit sanitization or validation of the ingested file content is described in the workflow.

docs-generator