BC opg
Academic literature discovery and citation network analysis. Multi-source search across arXiv, DBLP, Semantic Scholar, and Google Scholar. Build citation networks (references from PDF parsing, citations from Google Scholar), get recommendations, monitor new papers, analyze topics, parse PDFs, import from Zotero, generate research summaries, export as BibTeX/CSV/Markdown/JSON, and generate interactive HTML graph visualizations. Use when user asks about finding papers, literature review, citation analysis, research trends, or visualizing citation networks.
As a process C 64/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
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 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
- 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-redirectable-api-keyservices/llm_client.py:83Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Edit Bash
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (opg) differs from the folder (release20260324)
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 65 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 3326 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 560: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 65 items
- +3Output format is stated explicitly
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.