BB alibabacloud-agentloop-management
The skill should be used when the user asks about Alibaba Cloud AgentLoop platform for onboarding applications into observability, managing Datasets, building pipelines, and evaluating.
The skill should be used when the user asks about Alibaba Cloud AgentLoop platform for onboarding applications into observability, managing Datasets, building…
As a process B 74/100 · Nearly there — weak spots: result and completion
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
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellreferences/ai.md:231Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Each framework provides a dedicated installer script (`curl -fsSL ... | bash`) that installs the corresponding observability plugin.
quoted -
medium Dangerous commands
cmd-pipe-to-shellreferences/evaluation/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-shellreferences/evaluation/evaluation.md:17Downloads 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](cli-installation-guide.md#first-time-install-or-major-upgrade). Avoid `curl | bash` piping.
quoted -
medium Dangerous commands
cmd-pipe-to-shellreferences/onboarding.md:22Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)2. If `upgrade` not available -> run `curl -fsSL --connect-timeout 10 --max-time 300 https://aliyuncli.alicdn.com/setup.sh | bash`, then re-check `aliyun version`.
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/pipeline/trace/ot-ai-collection-spec.md:226High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)| `gen_ai.conversation.id` | Unique conversation ID [3] | string | `conv…lPY` | Conditionally Required | |
tablefixture -
low Secrets in code
secret-high-entropy-tokenreferences/pipeline/trace/ot-ai-collection-spec.md:248High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)| `gen_ai.input.messages` | Model input content [9] | string | `[{"role": "user", "parts": [{"type": "text", "content": "Weather in Paris?"}]}, {"role": "assistant", "parts": [{"type": "tool_call", "itablefixture -
low Secrets in code
secret-high-entropy-tokenreferences/pipeline/trace/ot-ai-collection-spec.md:490High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)| `gen_ai.tool.call.id` | Tool call ID | string | `call…5H4` | Recommended | |
tablefixture -
low Secrets in code
secret-high-entropy-tokenreferences/pipeline/trace/ot-ai-collection-spec.md:528High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)| `gen_ai.conversation.id` | Unique conversation ID [3] | string | `conv…lPY` | Conditionally Required | |
tablefixture -
low Secrets in code
secret-high-entropy-tokenreferences/pipeline/trace/ot-ai-collection-spec.md:530High-entropy token-like string (may be an id, hash or a credential) (documentation table row; test fixture / example file)| `gen_ai.agent.id` | Unique agent identifier | string | `asst…lPY` | Conditionally Required | |
tablefixture
Files scanned: 71. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 74/100
- 0Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 20 steps
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1989 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 185: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 20 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.