podwise

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests and reads public third-party content — e.g., workflows (episode-notes, language-learning, topic-research, catch-up, etc.) require running podwise process on YouTube/Xiaoyuzhou or other external URLs and calling podwise get transcript / podwise get summary to read those transcripts/artifacts, so untrusted web-hosted, user-generated content is parsed and used to drive decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation instructions tell the user to run a remote install script and fetch source at runtime (e.g. curl -sL https://raw.githubusercontent.com/hardhackerlabs/podwise-cli/main/install.sh | sh and git clone https://github.com/hardhackerlabs/podwise-cli.git), which would fetch and execute remote code as a required setup dependency and thus presents a runtime-executed external dependency risk.