CD li-feishu-audio
飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别，Edge TTS 进行语音合成，自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。
As a process D 41/100 · Unfinished process — 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 17
✓ No critical or high findings
Medium and low: 17
-
medium Exfiltration
net-credential-usescripts/feishu-tts.sh:72Credential used in a network call (verify the destination is the intended service)ACCESS_TOKEN=$(curl -s -X POST "$TOKEN_URL" \
-
medium Dangerous commands
cmd-pipe-to-shellscripts/install-with-model-choice.sh:127Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# 安全安装：下载到临时文件后执行，避免直接 curl|sh
comment -
medium Dangerous commands
cmd-pipe-to-shellscripts/install.sh:127Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)# 安全安装：下载到临时文件后执行，避免直接 curl|sh
comment -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_AUDIT_COMPLETE.md:10Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| 供应链攻击 (curl\|sh) | 🔴 P0 - 高危 | ✅ 已修复 |
security skill -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_AUDIT_COMPLETE.md:158Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)# 2. 检查 curl|sh
security skill -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_FIXES_0.1.6.md:29Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)### 2. ✅ 供应链攻击 - curl|sh (P0)
security skill -
medium Dangerous commands
cmd-pipe-to-shellSECURITY_FIXES_0.1.6.md:107Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)# 检查 curl|sh 使用情况
security skill -
low Exfiltration
read-dotenvREADME_EN.md:66Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvREADME_EN.md:76Reads a .env filesource .env
-
low Exfiltration
read-dotenvREADME.md:66Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvREADME.md:76Reads a .env filesource .env
-
low Exfiltration
read-dotenvscripts/MODEL_CHOICE.md:91Reads a .env filesource scripts/.env
-
low Exfiltration
read-dotenvSECURITY_CONFIG.md:22Reads a .env file (documentation of a security skill)cp .env.example .env
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostSECURITY_FIXES_0.1.6.md:40Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -sSf https://astral.sh/uv/install.sh | sh # ❌ 直接执行远程代码
security skill -
low Exfiltration
read-dotenvSECURITY.md:34Reads a .env file (documentation of a security skill)cp .env.example .env
security skill -
low Exfiltration
read-dotenvSECURITY.md:40Reads a .env file (documentation of a security skill)source .env
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 33. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 41/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (li-feishu-audio) differs from the folder (li-feishu-qq-audio)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 71 steps
- 100Execution cost. Instruction body is 1649 tokens
- 100Progress reporting. Reports progress
- low 19 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
- -223 emoji in the instructions: noise for the model
- -33 of 10 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 154: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.