Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md sibling scenario skill: this skill packages only its `SKILL.md` and
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Ofox video-generation workflow that asks for cost approval before paid API calls and does not show hidden persistence or destructive behavior.
Before installing, understand that this skill can spend money through your Ofox account after approval and depends on a separate ofox-video-core skill for the actual API script. Review cost tables before approving runs, use an explicit output directory, and install missing dependencies yourself rather than letting an agent run installer commands silently.
Referenced artifact was not completely inspected
sibling scenario skill: this skill packages only its `SKILL.md` and
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Lines L044-L046 explicitly state 'Nothing here writes a prompt' and the surrounding section repeatedly says prompt writing belongs to scenario skills. Later, L657-L659 says 'This skill drafts a prompt; it doesn't write one,' which contradicts the earlier documentation about the skill's role.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
| anime or manga-styled | [`seedance-anime-drama`](../seedance-anime-drama/SKILL.md) |
| ambient / mood b-roll — no product, no people, no beat: rain on a window, steam off a cup, a city at dusk | **no scenario skill owns this.** Go straight to the shared craft: [`prompt-structure.md`](../ofox-video-core/references/prompt-structure.md) → `The vendor's own formula (ByteDance first-party)` for the four-sentence template, `Style anchor — the texture layer` for the look, `Camera language` for the move |
Write it there, run the set through here. The two things this skill adds on
top are **vertical** and **cheap enough to throw most of them away** — and
that second one is the whole reason it exists separately.