BA rube
Use Rube tools. Triggers on: RUBE_FIND_RECIPE, RUBE_MANAGE_RECIPE_SCHEDULE, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_BASH_TOOL, RUBE_REMOTE_WORKBENCH, RUBE_SEARCH_TOOLS, RUBE_GET_TOOL_SCHEMAS, RUBE_CREATE_UPDATE_RECIPE, RUBE_EXECUTE_RECIPE, RUBE_GET_RECIPE_DETAILS.
As a process A 80/100 · Runs to the end — weak spots: execution cost, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl:*)allowed-tools: Bash(curl:*)
-
low Obfuscation
obf-base64-blobscripts/rube.sh:17Long base64-looking blob (quoted — discussed, not commanded)-H "Authorization: Bearer eyJh…02I
quoted -
low Obfuscation
obf-base64-blobscripts/rube.sh:29Long base64-looking blob (quoted — discussed, not commanded)-H "Authorization: Bearer eyJh…02I
quoted -
low Obfuscation
obf-base64-blobscripts/rube.sh:36Long base64-looking blob (quoted — discussed, not commanded)-H "Authorization: Bearer eyJh…02I
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10348 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 80/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 27 mutating operations with no state check
- 40Execution cost. Instruction body is 10348 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 174 steps, 3 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 30 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 286: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 174 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.