70High
This skill uses unauthorized sub-agent spawning to bypass safety filters, hides backend decisions from users, executes unconstrained commands, and relies on external, unverified content sources.
HygienePackaging & Manifest6 findings
Skill Info
Nameheygen-com/hyperframes/embedded-captions
Registrygithub
Versiona4303137cbce
PURLpkg:github/heygen-com/hyperframes@a4303137cbce?skill=embedded-captions
Stars32,324
Installs48,300
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
48,300 installs
Skills.shDocs
npx skills add https://github.com/heygen-com/hyperframesAssessments (5)
AI Agent Traps ↗Hidden capability via sub-agent spawninghighsub agent spawningAML.T0053AML.T0051.001LLM06:2025
The instructions explicitly direct the agent to spawn sub-agents for visual QA, which can be used to bypass the primary agent's safety constraints by providing a limited, attacker-controlled prompt to the sub-agent. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
90% confidenceline 163
If you can spawn a subagent, give it ONLY the preview sheet + this checklist and ask for PASS/FIX verdicts
Sub-agent spawning instructions detected — may create agents with attacker-controlled promptsmediumsub agent spawningAML.T0053AML.T0051.001LLM06:2025
Sub-agent spawning instructions detected — may create agents with attacker-controlled prompts
95% confidenceline 163
spawn a subagent
Long base64-encoded blob detected (potential hidden payload)mediumobfuscationAML.T0068AML.T0015LLM01:2025
Long base64-encoded blob detected (potential hidden payload)
95% confidenceline 3
anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity
Implicit instruction to bypass human oversightlowoversight evasionAML.T0054LLM01:2025LLM07:2025
The instructions explicitly tell the agent to 'never surface' certain modes or choices to the user, forcing the agent to make backend decisions without human transparency.
80% confidence
Never surface 'Standard vs Cinematic vs Theme' as a question — those are backend names (a product has one UX even with several engines).
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "CATALOG.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[CATALOG.md](CATALOG.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/composition-craft.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/composition-craft.md](references/composition-craft.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/rail.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/rail.md](references/rail.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/reference-bar.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/reference-bar.md](references/reference-bar.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "themes/README.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[themes/README.md](themes/README.md)
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/heygen-com/hyperframes/embedded-captions)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/heygen-com/hyperframes/embedded-captions"><img src="https://mondoo.com/ai-agent-security/api/badge/github/heygen-com/hyperframes/embedded-captions.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/heygen-com/hyperframes/embedded-captions.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow