CF linkmind-capture
Capture social media links (Weibo, Xiaohongshu, WeChat, Xiaoyuzhou) — extract text, images, and metadata, then generate a Markdown note with AI deep summary, saved to the user's Obsidian vault.
As a process F 60/100 · Will not run — References files that are not bundled: attachments/{date}-{slug}/img-001.jpg, original_url, attachments/{date}-{slug}/img-NNN.jpg
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 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 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 · 7
-
high Exfiltration
intent-browser-credential-storeskill-card.md:22Accesses a browser credential / cookie storeRisk: The skill may use platform cookies and a local Chrome debugging session to access supported sites. <br>
Medium and low: 6
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Shellallowed-tools: Shell Read Write Glob Grep
-
low Secrets in code
secret-high-entropy-tokenscripts/package-lock.json:92High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"integrity": "sha5…cAz+ivBu…Lvw==",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/package-lock.json:177High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"integrity": "sha5…IxX/wd5n…MGF+pv6g…i2Z+Wnj9/KjGz…4Eg==",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/package-lock.json:211High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"integrity": "sha5…BQM/qZ3R+9TEU…es4+qu1b…BFA==",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/package-lock.json:228High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"integrity": "sha512-8mL/vh8q…uJP+ZcVY…AJW+m0Et…WzA==",
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/package-lock.json:245High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"integrity": "sha5…NES+HiD4…TOe+/2rdn…PWn/r/aAw==",
quoted
Files scanned: 25. 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") - warning
body-longSKILL.md body ≈ 5211 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: attachments/{date}-{slug}/img-001.jpg - warning
missing-refreference to a missing file: original_url - warning
missing-refreference to a missing file: attachments/{date}-{slug}/img-NNN.jpg - warning
missing-refreference to a missing file: ... - warning
missing-refreference to a missing file: attachments/{date}-{slug}/img-002.jpg - warning
missing-refreference to a missing file: attachments/{date}-{slug}/transcript.srt - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 60/100
- 0Tools and files. 6 referenced file(s) missing: attachments/{date}-{slug}/img-001.jpg, original_url, attachments/{date}-{slug}/img-NNN.jpg
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5211 tokens
- 100Steps. 88 steps
- 100Failures and branches. 17 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
- low 15 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)
- -310 of 16 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 193: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 88 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.