SKILLEMALL.ai

BF sciverse-academic-retrieval

Sciverse academic paper retrieval: structured metadata search, semantic chunk retrieval for RAG, and character-range content reading (offsets in Unicode code points). For agent workflows that need citation-grade scientific literature.

ClawHub Agent Skills author: Sciverse v0.14.2 MIT-0 11 files body ≈ 2 227 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process F 40/100 · Will not run — References files that are not bundled: file_name, dt=xxx/p/f3.png

ProcedureResearchAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
95
Quality 40%
61
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: file_name, dt=xxx/p/f3.png
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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".

For the author

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

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Exfiltration net-redirectable-api-key scripts/_common.mjs:13
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 4, column 14: description: Sciverse academic paper retrieval: structured metadata search, sem… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning missing-ref reference to a missing file: file_name
  • warning missing-ref reference to a missing file: dt=xxx/p/f3.png
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: file_name, dt=xxx/p/f3.png
  • 0Tools and files. 2 referenced file(s) missing: file_name, dt=xxx/p/f3.png
  • 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
  • 40Consistency. Frontmatter name (sciverse-academic-retrieval) differs from the folder (academic-retrieval)
  • 100Steps. 6 steps
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 2227 tokens
  • 100Running it twice. Mutating operations check current state
  • low The response is described with custom markup (6 tags): a typed call is more reliable

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
  • -31 of 7 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 234: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 6 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: suspicious
The skill appears to perform legitimate Sciverse academic retrieval, but it needs review because a base-URL override can send its API token over unencrypted HTTP.
LLM: suspicious (high) · 11 Sept 2026