hindsight-upgrade

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

• Third-party content exposure detected (high risk: 0.90). The skill's update-check script (bin/hindsight-update-check) fetches a remote VERSION from the public URL https://raw.githubusercontent.com/vectorize-io/hindsight-skills/main/VERSION using curl/wget and uses that value to signal UPGRADE_AVAILABLE which can trigger git pull/clone from GitHub and run ./setup, so untrusted remote content directly influences upgrade actions and execution.

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

• Potentially malicious external URL detected (high risk: 0.90). The vendored upgrade path clones and then runs the fetched repository's setup script — e.g., git clone https://github.com/vectorize-io/hindsight-skills.git followed by ./setup — which fetches remote code at runtime and executes it, so the URL is a high-risk runtime dependency.