The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git diff commands. This is used strictly to retrieve changes in content files (.md, .html) for review purposes, which is consistent with its stated functionality.
[DATA_ACCESS]: The skill accesses local content directories such as bazy-wiedzy/ and aktualnosci/ using Read, Grep, and Glob tools. This file access is limited to content files and is required for the skill's primary purpose of reviewing text.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diff outputs and user-provided files.
Ingestion points: Git diff output, files in content directories, and user-provided text.
Boundary markers: None explicitly defined to separate instructions from content.
Capability inventory: Bash, Read, Grep, Glob tools are available.
Sanitization: No explicit sanitization or filtering of the ingested content is described. While this creates a surface for indirect prompt injection, it is common for review-oriented skills.

marko-pl-content