AC identity
UserPool login, TIP token, credential hosting, and tool risk approval. Activate when user needs to check identity (whoami/status), log in, list/add credentials, manage env bindings, configure the plugin, or diagnose/approve risky tool calls. Also activates for: 用户说登录、查身份、获取凭据、添加/配置API密钥、绑定环境变量、配置插件、审批工具调用、风险检查.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:68Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)- **Rule-based**: Destructive patterns (rm -rf, sudo, curl|bash), sensitive paths (/etc, ~/.ssh).
detector
Files scanned: 2. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (identity) differs from the folder (volcengine-agent-identity)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 17 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 3463 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
- +1No license
- +2Single-language instructions
- +3Description length 312: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.