The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructs the agent to read and exploit information from local files such as .agents/product-marketing.md and .claude/product-marketing.md. This ingestion of untrusted data from the project environment constitutes an indirect prompt injection surface. * Ingestion points: The agent is directed to search for and read marketing context files before initiating the task. * Boundary markers: No delimiters or safety instructions are provided to ensure the agent ignores malicious commands that could be embedded in these context files. * Capability inventory: The agent possesses the capability to generate implementation code and tracking plans, which could be subverted by injected instructions. * Sanitization: There is no evidence of validation or sanitization of the content retrieved from the context files.
[EXTERNAL_DOWNLOADS]: The skill references multiple external resources hosted on GitHub that appear to be deceptive. * Evidence: The skill links to integration guides and a tool registry at https://github.com/mbzadev/skills. * Deception Pattern: The GitHub organization name mbzadev is a character-omission typosquat of the stated author mabzadev (missing the second 'a'). This matches patterns of impersonation of vendor infrastructure, posing a supply chain risk.

analytics