CF alibabacloud-vms-smart-call-by-tts
Alicloud VMS Smart Voice Call Skill. Use for making AI-powered voice calls with natural language intent. The system automatically matches contacts from the address book and generates call content via LLM. Triggers: "智能语音通知", "AI 打电话", "smart voice call", "SubmitIntent", "给某人打电话", "语音通知提醒".
Alicloud VMS Smart Voice Call Skill.
As a process F 58/100 · Will not run — References files that are not bundled: references/*.md
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.
- The text references files that are not there: add them or drop the references.
- 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-privilegereferences/cli-installation-guide.md:45Privilege escalation / world-writable permissionssudo mv /tmp/aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:55Privilege escalation / world-writable permissionssudo mv /tmp/aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:95Privilege escalation / world-writable permissionssudo mv /tmp/aliyun /usr/local/bin/
-
medium Dangerous commands
cmd-privilegereferences/plugin-troubleshooting.md:120Privilege escalation / world-writable permissionssudo chown -R $(whoami):$(id -gn) ~/.aliyun
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:74Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> - **Do not** run `curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash` to install the CLI: piping a remote script directly to a shell **bypasses integrity verification and is treated as a securi
quoted -
low Dangerous commands
cmd-shell-rcreferences/cli-installation-guide.md:77Writes to a shell startup file (detector / deny-list definition)grep -qsF "$DEST" ~/.zshrc || echo "export PATH=\"$DEST:\$PATH\"" >> ~/.zshrc
detector -
low Dangerous commands
cmd-shell-rcreferences/cli-installation-guide.md:115Writes to a shell startup file (detector / deny-list definition)grep -qsF "$DEST" ~/.bashrc || echo "export PATH=\"$DEST:\$PATH\"" >> ~/.bashrc
detector -
low Dangerous commands
cmd-pipe-to-shellscripts/install_aliyun_cli.sh:11Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)# (no sudo, no brew, no `curl | bash`).
negated -
low Dangerous commands
cmd-pipe-to-shellscripts/install_aliyun_cli.sh:79Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)# destination; this is NOT `curl | bash`. No remote script is ever executed.
negated
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9085 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/*.md - note
edit-residuethe text marks something as outdated (lines 17, 127, 252): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Tools and files. 1 referenced file(s) missing: references/*.md
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 9085 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 37 steps, 1 vague phrases
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -219 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 290: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.