The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to maintain repository state, specifically git fetch, git pull --rebase, and git stash in the SKILL.md file. These commands are part of a standard synchronization workflow for developer-oriented AI agents.
[EXTERNAL_DOWNLOADS]: The agent interacts with well-known registries such as npm, PyPI, and Homebrew via their public APIs. These downloads are used to check for package namespace collisions and are performed against established, trusted technological services.
[PROMPT_INJECTION]: The skill possesses a surface area for indirect prompt injection because it ingests and processes text data from external websites (social profiles, registry descriptions, and trademark results).
Ingestion points: Data retrieved via WebSearch and WebFetch from social media platforms, package registries, and trademark databases, as well as the local prd.md file.
Boundary markers: Absent; external data is interpolated into the context of sub-agents without the use of explicit delimiters or instructions to ignore embedded commands.
Capability inventory: Includes the ability to execute git shell commands and perform subsequent network operations through web search and fetch tools.
Sanitization: Names are normalized into a slug format (lowercase with hyphens), but there is no specific sanitization or filtering applied to the descriptive text content retrieved from external sources.

name-checker