archon

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

• Third-party content exposure detected (high risk: 0.75). The required runtime path for this skill is executing Archon workflows (e.g., archon workflow run ...), where the agent can ingest outsider-authored free text from GitHub issue/PR bodies/comments via platform context variables like $CONTEXT/$ISSUE_CONTEXT (and/or tool outputs such as gh issue view ... --json title,body,comments) into the LLM prompt.

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

• Potentially malicious external URL detected (high risk: 0.90). The setup guide instructs running the Bun installer directly from the network (curl -fsSL https://bun.sh/install | bash and irm bun.sh/install.ps1 | iex), which fetches and executes remote code at runtime to satisfy a required dependency (bun).