SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The code intentionally encodes and sends local video frames and system metadata to an arbitrary VLM server URL (AEGIS_VLM_URL / --vlm), which is a clear data-exfiltration vector if the endpoint is untrusted or attacker-controlled.
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
The required runtime workflow (“Skill → Aegis downloads video clips, samples frames, evaluates with VLM, and generates an HTML report”) ingests the outsider-authored YouTube clip text metadata/description from `fixtures/annotations.json`/downloaded media as inputs for evaluation, which then produces free-form reasoning text in `scripts/run-benchmark.cjs` via `vlmCall()` and is included in the LLM context through `messages` (system+user) for VLM chat.
- Repository
- SharpAI/DeepCamera
- Commit
2264fcb
- 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.