T09 · Insecure Skill Coding Practices
- Location
workflow.json:81- Finding
External Publication Proceeds Without a Final User-Approval Gate
- Content
View full analysis
Vulnerability Details
File Location:
workflow.json:81-89
Vulnerability Type: Missing authorization checkpoint before an external side effect
Risk Level: Mediumjson { "id": 5, "name": "Xiaohongshu publication", "skill": "xiaohongshu-mcp", "action": "publish", "prompt": "Rewrite the article as a Xiaohongshu image-and-text post and publish it", "next": "complete" }The snippet above is an English rendering of the original configuration values. The control fields, skill identifier, action, and transition are unchanged.
Technical Analysis
The final workflow step invokes the authenticated
publishaction directly and then transitions to completion. Unlike the topic-selection step, it does not defineuser_intervention, an approval state, a draft-only action, or any other explicit authorization checkpoint.This configuration is inconsistent with the accompanying documentation, which states that the assistant asks whether the user wants to publish and suggests that final publication requires confirmation. Security-sensitive behavior is governed by the executable workflow configuration rather than by descriptive documentation. Consequently, an orchestrator that follows
workflow.jsoncan publish generated content immediately after the preceding steps.The workflow also feeds externally researched material through generative transformations before publication. Inaccurate, adversarially influenced, or otherwise unsuitable source material may therefore reach an authenticated external account without the user reviewing the final text, images, tags, target account, or visibility settings.
Attack Path
- The search skill collects externally controlled or misleading content concerning the selected topic.
- The user confirms the general topic at the only explicitly configured intervention point.
- Downstream skills generate an article, cover image, and platform-specific adaptati ...[truncated 1242 chars]
- Remediation
View remediation
Remediation Suggestions
- Insert a mandatory user-intervention step immediately before any external publication action.
- Split publication into separate
prepare_draftandpublishoperations. The default workflow must stop after draft preparation. - Present the exact final text, images, tags, target platform account, visibility, and other publication settings to the user.
- Require an explicit, affirmative confirmation tied to that exact payload. Editing the payload should invalidate prior approval and require confirmation again.
- Add a configuration control such as
user_intervention: trueand an unambiguous intervention label such asfinal_publication_approval. - Fail closed when approval is absent, expired, ambiguous, or cannot be associated with the current draft.
- Ensure the external publication skill operates with the minimum account permissions necessary and does not reuse authorization granted for unrelated content.
- Add automated workflow tests verifying that execution cannot reach
action: "publish"without a recorded approval event. - Update the workflow and documentation together so that the configured behavior consistently matches the stated final-review requirement.
