The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The installation instructions direct the agent or user to clone a repository from an external source (github.com/fhuber82/apexbank-analytics-hub.git) which is not identified as a trusted vendor.
[COMMAND_EXECUTION]: The skill instructs the execution of shell commands to set up the environment, including git clone and starting local web servers using Python (python -m http.server) or Node.js (npx http-server).
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect injection via untrusted data processing. It ingests data from localStorage and user-submitted forms to render dashboard elements.
Ingestion points: Data is loaded from localStorage in AccountManager, TransactionManager, and SavingsGoalManager, as well as from HTML forms via FormData in TransferManager and MortgageCalculator.
Boundary markers: No boundary markers or instructions to ignore embedded commands are present when processing external data.
Capability inventory: The skill possesses the capability to write to the DOM (innerHTML) and trigger downloads (Blob/URL.createObjectURL).
Sanitization: There is no evidence of sanitization or escaping of external content before it is interpolated into the DOM.
[DYNAMIC_EXECUTION]: The JavaScript code snippets provided in SKILL.md use .innerHTML to render data from account.name, txn.description, and goal.name. This pattern is vulnerable to Cross-Site Scripting (XSS) if the data source (e.g., a transaction description) contains malicious script tags.

apexbank-analytics-dashboard