AF research-assistant
Enrich Bear research notes tagged 「待整理」 with thematic GIFs. Use when the user wants to auto-illustrate or spruce up draft research notes in Bear, or mentions "待整理", "research notes", "add GIFs to notes", or "enrich notes".
As a process F 52/100 · Will not run — References files that are not bundled: <gif_url>
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.
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-credential-usescripts/enrich_notes.sh:107Credential used in a network call (verify the destination is the intended service)GIF_RESULT=$(curl -s "${GIF_API}?api_key=${GIF_KEY}&q=${ENCODED_KW}&limit=3" 2>/dev/null) -
low Secrets in code
secret-password-literalSKILL.md:24Hard-coded password / key literal (may be an example) (placeholder value)c. For each keyword, search GIFs using the gifgrep skill (or `curl "https://api.giphy.com/v1/gifs/search?api_key=…&q=<keyword>&limit=3"` as fallback).
placeholder
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: <gif_url>
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: <gif_url>
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (research-assistant) differs from the folder (bear-research-enricher)
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 12 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 525 tokens
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
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 222: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.