video-analyser
Analyses a video — usually a bug screen recording from a file, URL, or Linear ticket — with ffmpeg keyframes plus optional OCR and transcription, extracting errors, UI state, and repro steps. Triggers on "analyse this video", "analyze this recording", "what does this video show", "/video-analyser".
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 workflow reads external Linear issues and comments via MCP and downloads attachments from URLs provided by outsiders.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill instructs the agent to download and execute code or scripts via `curl` from user-supplied or external URLs during runtime (`curl -fL -o "$WORK_DIR/input.mp4" "$INPUT"` and `$ATTACHMENT_URL`), representing an arbitrary or uncontrolled inbound operational dependency.
- Repository
mthines/agent-skills
- Revision
0ec47ca
- 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.