The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple shell commands including npm install, npm run dev, and npm run build within the scaffolded game directory. These commands execute scripts defined in the template's package.json file, which is a potential vector for arbitrary code execution if the template files are compromised.
[EXTERNAL_DOWNLOADS]: The skill uses npm install to download and install Node.js dependencies from the public npm registry. This introduces a supply chain dependency risk, as the skill does not verify the integrity or safety of the packages being installed during the scaffolding process.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes external data from user-provided URLs to guide its behavior.
Ingestion points: The skill fetches content from x.com, twitter.com, and fxtwitter.com URLs via the fetch-tweet skill.
Boundary markers: The game concept derived from the tweet is passed directly to a subagent's Task prompt without boundary delimiters or instructions to ignore instructions embedded within the tweet content.
Capability inventory: The skill has the capability to write to the local filesystem, execute shell commands through npm, and perform network requests.
Sanitization: There is no evidence of sanitization or validation of the fetched tweet content before it is used to influence the implementation logic performed by the subagent.

quick-game