DF shequn-shoulu
青木会江湖社群小青，温柔轻声细语地帮助群主完成社群信息收录，自动同步到IMA知识库，让优质社群被更多人找到。支持校友会/商协会/企业社群/个人兴趣四类模板。
青木会江湖社群小青，温柔轻声细语地帮助群主完成社群信息收录，自动同步到IMA知识库，让优质社群被更多人找到。支持校友会/商协会/企业社群/个人兴趣四类模板。
As a process F 33/100 · Will not run — References files that are not bundled: references/qingmu_intro.md, references/{类型}_template.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 7
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:699Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://skillhub.cn/install/install.sh | bash
Medium and low: 6
-
medium Secrets in code
secret-labelled-tokenSKILL.md:342Labelled token / key literal (vendor format unknown — verify it is not a live credential)API_KEY = RltO…uwp+ViJu…szQ==
-
medium Secrets in code
secret-labelled-tokenSKILL.md:391Labelled token / key literal (vendor format unknown — verify it is not a live credential)API_KEY = "RltO…uwp+ViJu…szQ=="
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:342High-entropy token-like string (may be an id, hash or a credential)API_KEY = RltO…uwp+ViJu…szQ==
-
low Secrets in code
secret-password-literalSKILL.md:342Hard-coded password / key literal (may be an example)API_KEY = RltO…uwp+ViJu…szQ==
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:391High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)API_KEY = "RltO…uwp+ViJu…szQ=="
quoted -
low Secrets in code
secret-password-literalSKILL.md:391Hard-coded password / key literal (may be an example)API_KEY = "RltO…uwp+ViJu…szQ=="
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
name-missingSKILL.md: frontmatter has no `name` - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/qingmu_intro.md - warning
missing-refreference to a missing file: references/{类型}_template.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "trigger"
Process rating: all ten parameters 33/100
- 0Tools and files. 2 referenced file(s) missing: references/qingmu_intro.md, references/{类型}_template.md
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 100Steps. 84 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3780 tokens
- low 17 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)
- +3Description length 78: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -256 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Structure: 46 headings
- +3Step-by-step instructions: 84 items
- +4Has examples (25 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 22.