BB membase
Manage agent memory with Membase - a decentralized, encrypted memory backup and restore system. Provides backup, restore, list, diff, status, and cleanup operations for agent memories.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: bashallowed-tools: bash
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:101High-entropy token-like string (may be an id, hash or a credential)Backup ID: back…23Z
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:129High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)User: "Restore my memories from back…23Z"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:140High-entropy token-like string (may be an id, hash or a credential) (placeholder value)node membase.ts restore back…23Z --password "<password>"
placeholder -
low Secrets in code
secret-high-entropy-tokenSKILL.md:179High-entropy token-like string (may be an id, hash or a credential)back…23Z 2026-02-02 10:30:45 15 234 KB
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:180High-entropy token-like string (may be an id, hash or a credential)back…56Z 2026-02-01 15:20:10 12 198 KB
Files scanned: 10. 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 65/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (membase) differs from the folder (unibase-membase)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 67 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2167 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 184: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (29 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.