skill-library

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill fetches and parses the public armory manifest from https://raw.githubusercontent.com/Mathews-Tom/armory/main/manifest.yaml and then uses those untrusted catalog entries (names, paths, descriptions, and source locations) to decide which packages to fetch/install (via git/gh/curl), so third‑party content can directly influence tool use and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches and installs remote package content at runtime from URLs such as https://raw.githubusercontent.com/Mathews-Tom/armory/main/manifest.yaml and https://github.com/Mathews-Tom/armory.git (via git/gh/curl), which are required at runtime to retrieve SKILL.md and other skill files that can contain prompts or executable code and therefore can directly control agent behavior.