The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill downloads an installation script from the author's GitHub repository and executes it by piping the content directly to the bash shell.
[COMMAND_EXECUTION]: The skill performs several system-level operations, including installing packages via Homebrew, managing local directories, and executing remote commands on a VPS through SSH.
[EXTERNAL_DOWNLOADS]: Fetches installation scripts and release information from 'raw.githubusercontent.com' and uses the GitHub CLI to retrieve repository metadata.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could be exploited to influence the agent's behavior if those sources were compromised.
Ingestion points: Release tags and metadata fetched via the GitHub CLI, and the contents of local .env files during security testing (SKILL.md).
Boundary markers: No explicit delimiters or isolation instructions are provided when processing external data.
Capability inventory: The skill has the ability to execute shell commands, perform network requests, and run remote commands via SSH (SKILL.md).
Sanitization: There is no evidence of validation or sanitization of the data retrieved from GitHub before it is used in subsequent operations.

test-release