cheat-shoot
登记一条视频已拍摄。**建 video folder + 询问实际拍摄稿是否与 scripts/<id>.md 一致 + buffer +1**。与 cheat-publish 配对：拍了进队列，发了出队列。触发词："拍了"/"拍了 X"/"shot"/"shot it"/"已拍 X"/"录完了"。
68
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In SKILL.md Phase 2/3, the workflow prompts the user to “give me the actual shot script” (paste text / file path / transcript) and then writes it into `videos/<id>/script.md`, which is later passed into `/cheat-predict — mode: v2` (Phase 3b, step 5), so this runtime ingests outsider-authored free text (the user’s pasted filming transcript/content) into the agent/LLM context via the delegated prediction step.
- Repository
- XBuilderLAB/cheat-on-content
- Commit
86823e1
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.