FC zettabrain-rag
Query documents on your NFS shares, SMB servers, or local drive using local AI. No cloud, no Docker, no API keys — the only RAG skill that reads from enterprise storage directly. Runs on your own machine with Ollama + ChromaDB.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
- 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 · 11
-
high Dangerous commands
cmd-persistenceSKILL.md:163Persistence mechanism (cron / launchd / scheduled task / autorun registry)sudo launchctl unload /Library/LaunchDaemons/io.zettabrain.server.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:166Persistence mechanism (cron / launchd / scheduled task / autorun registry)sudo rm /Library/LaunchDaemons/io.zettabrain.server.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:182Persistence mechanism (cron / launchd / scheduled task / autorun registry)sudo launchctl unload /Library/LaunchDaemons/io.zettabrain.server.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:183Persistence mechanism (cron / launchd / scheduled task / autorun registry)sudo rm -f /Library/LaunchDaemons/io.zettabrain.server.plist
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:50Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://zettabrain.app/install.sh | sudo bash
vendor-host -
medium Dangerous commands
cmd-privilegeSKILL.md:50Privilege escalation / world-writable permissionscurl -fsSL https://zettabrain.app/install.sh | sudo bash
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:53Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://zettabrain.app/install.sh | bash
vendor-host -
medium Dangerous commands
cmd-privilegeSKILL.md:156Privilege escalation / world-writable permissionssudo rm /etc/systemd/system/zettabrain.service
-
medium Dangerous commands
cmd-privilegeSKILL.md:166Privilege escalation / world-writable permissionssudo rm /Library/LaunchDaemons/io.zettabrain.server.plist
-
medium Dangerous commands
cmd-privilegeSKILL.md:179Privilege escalation / world-writable permissionssudo rm -f /etc/systemd/system/zettabrain.service && sudo systemctl daemon-reload
-
medium Dangerous commands
cmd-privilegeSKILL.md:183Privilege escalation / world-writable permissionssudo rm -f /Library/LaunchDaemons/io.zettabrain.server.plist
Files scanned: 2. 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") - note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1743 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 227: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.