BB openclaw-magika
AI-powered file type detection. Detects file content types (200+ types, ~99% accuracy) using Google Magika deep learning model. Triggered when: (1) user asks to identify/check/detect file type, (2) analyzing uploaded files, (3) batch classifying files by content. Requires: magika CLI (pip install/pipx install/brew). Reads: no config files. No data sent to third parties; local inference only.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 1
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:59Downloads and executes remote code from an unrecognised host (pipe to shell)curl -LsSf https://securityresearch.google/magika/install.sh | sh
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Unexpected flow-map-end token in YAML stream: "}" at line 3, column 72: metadata: {"openclaw":{"emoji":"🔍","requires":{"anyBins":["magika"]}}}} ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 367 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +3Description length 394: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 4 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.