The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various CLI tools including git, npx, cargo, gofmt, ruff, and black to perform its tasks. These are standard developer tools and their use is consistent with the skill's stated purpose of linting and formatting code.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of project source code files to identify linting errors, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Project files identified via git diff or provided directory paths in SKILL.md.
Boundary markers: None explicitly present to delimit ingested code content from agent instructions.
Capability inventory: Executes shell commands via npx, cargo, and other standard binaries as described in SKILL.md.
Sanitization: No explicit sanitization or filtering of the ingested file content is performed before processing.

lint