BC alibabacloud-agentloop-evaluation
Orchestrate AgentLoop evaluation workflows through the Aliyun CLI plugin with safe previews, saved evaluator and evaluator-skill management, one-shot sample tests, trace or dataset batch runs, polling, and result inspection. Analyze evaluation quality and low-score cases from SLS. Use for natural-language requests to create or update evaluators or evaluator skills, launch or monitor evaluation tasks, inspect evaluation results, diagnose low scores, troubleshoot evaluation API calls, and simplify AgentLoop evaluation commands.
Orchestrate AgentLoop evaluation workflows through the Aliyun CLI plugin with safe previews, saved evaluator and evaluator-skill management, one-shot sample…
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellreferences/cli-installation-guide.md:23Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> **Security note:** Avoid piping `curl` output directly into `bash` (`curl ... | bash`), as a compromised server or intercepted connection could execute arbitrary code on your machine. Always downloa
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:20Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> - **First install or major upgrade:** Download, review, then execute the [setup script](references/cli-installation-guide.md#first-time-install-or-major-upgrade). Avoid `curl | bash` piping.
quoted
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5496 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 54/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Execution cost. Instruction body is 5496 tokens
- 85Steps. 36 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 531: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.