smyx-elderly-nightmare-startle-detect-analysis@1.0.17
VERIFIED· install onlyPublisher claims: "Using a fixed bedroom camera (infrared night vision + microphone), the system analyzes elderly nighttime sleep video and detects abnormal events such as sudden sitting-up (quick lying-to-sitting transition), screams (high-pitched short cries), and arm-thrashing (purposeless rapid arm movements), and records the occurrence time, frequency and duration of each event. | 通过卧室固定摄像头(红外夜视),分析老年人夜间睡眠视频,检测突然坐起(快速从躺卧变为坐立)、惊叫声音(高频短促叫声)以及挥舞手臂(无目的性的快速手臂动作)等行为,记录发生时间、频次及持续时间。该技能可帮助家属或护理人员了解老人夜间睡眠质量,识别可能的梦魇、快速眼动期睡眠行为障碍等异常现象,为医疗评估提供参考。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 13 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 1.0.15
vet-skills diff smyx-elderly-nightmare-startle-detect-analysis 1.0.15 1.0.17In the sandbox, this version reached for nothing 1.0.15 did not. Compared from the two recorded runs, not from source.
1.0.15 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
# result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.base-url-health: "http://192.168.1.234:7070/jeecg-boot-xzgz"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.| 🧑⚖️ 结果性质 | 红线约束:**禁止**输出 RBD / 帕金森病 / 阿尔茨海默病 / 睡眠呼吸暂停综合征等任何医学诊断;**禁止**根据本工具结果调整药物;**禁止**长期存储夜间原始视频 |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.base-url-open-api: "http://192.168.1.234:9601/smyx-open-api"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.base-url-open-h5: "http://192.168.1.234:4100"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.