The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill uses npx @orrisai/show-me-the-money@latest update to download and execute a remote package from the npm registry. This provides a direct path for executing code from an external source that is not part of the platform's trusted vendor list.
[PRIVILEGE_ESCALATION]: The skill instructs the agent to suggest a sudo command (sudo chown -R $(whoami) ~/.claude/) to the user if a permission error (EACCES) is encountered. Suggesting or executing commands with root privileges is a high-risk pattern.
[EXTERNAL_DOWNLOADS]: The skill fetches files from external sources, specifically raw.githubusercontent.com and the npm registry. These downloads include the update package itself and release documentation (CHANGELOG.md).
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
Ingestion points: The curl command fetches the CHANGELOG.md file from raw.githubusercontent.com/iamzifei/show-me-the-money/ and the npm view command retrieves version metadata from the npm registry.
Boundary markers: None. The content fetched from the remote changelog is summarized and presented to the agent's context without delimiters or warnings to ignore embedded instructions.
Capability inventory: The skill has the ability to execute shell commands (npx, npm, cat), access the local file system (~/.claude/skills/), and perform network requests via curl and npm.
Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the agent.

money-upgrade