algorand-project-setup

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

• Third-party content exposure detected (high risk: 0.70). The skill’s workflow and docs (references/github-search-tools.md) require using GitHub retrieval/search tools like github_get_file_contents and github_search_code to fetch public repository files (examples reference algorandfoundation/puya-ts and devportal-code-examples), so the agent ingests public GitHub content that can materially influence project setup 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 calls GitHub file-fetching at runtime (e.g., github_get_file_contents owner:algorandfoundation repo:puya-ts path:...) which will retrieve repository files (e.g., via GitHub raw URLs such as https://raw.githubusercontent.com/algorandfoundation/puya-ts/...) and those fetched files are relied on to provide code/examples that are injected into the agent's context and thus can directly control agent instructions.