project-sync

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public GitHub content (e.g., using gh API calls to repo contents and the default source https://raw.githubusercontent.com/cleaniquecoders/kickoff/... referenced in /project-sync status/diff/update and the --source URL option), which is untrusted, user-controlled third-party content that the agent reads and uses to drive merges, decisions, and commits.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches the source CLAUDE.md at runtime from https://raw.githubusercontent.com/cleaniquecoders/kickoff/refs/heads/main/stubs/CLAUDE.md and uses that fetched content as the authoritative source to drive merging/updating of project CLAUDE.md files (i.e., it directly controls the agent's merge actions and output and is relied on as the default required source), so this external URL is a runtime dependency that can control behavior.