SKILLEMALL.ai
RU Sign in

BB cerul

The video search layer for AI agents. Teach your AI agents to see — search video by meaning across speech, visuals, and on-screen text. Use when a user asks about what someone said or showed in a video, wants video evidence, or needs citations with timestamps.

ClawHub Agent Skills author: Jiaxi Cui v1.1.0 MIT-0 2 files body ≈ 945 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 76/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting

ProcedureMedia and videoAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
82
Run on models
none yet
Process rating
B
76/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Inputs and preconditions w 11
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Dangerous commands cmd-pipe-to-shell SKILL.md:40
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://cli.cerul.ai/install.sh | bash
      vendor-host
    • low Dangerous commands cmd-pipe-to-shell SKILL.md:26
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host; quoted — discussed, not commanded)
      command: "curl -fsSL https://cli.cerul.ai/install.sh | bash"
      vendor-hostquoted

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "when"
    • note frontmatter-key unknown frontmatter key "examples"

    Process rating: all ten parameters 76/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 17 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 4 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 945 tokens
    • 100Running it twice. Mutating operations check current state
    • low The skill ranks results itself: that belongs to the system behind the tool, not the model

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 260: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (5 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: suspicious
    This is a legitimate Cerul video-search skill, but it requires the agent to persist the user's API key locally instead of using the declared environment-variable secret path.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026