BC kannaka-node
Hand a fresh Linux server to an AI and get back a running Kannaka node. Given an IP or hostname and SSH access, the agent checks the box, installs the signed Kannaka release, writes the node's identity, wires it as a systemd service that joins the constellation swarm and keeps its memory in sync, dreams nightly, and proves it is alive before handing it back. Works on Oracle Cloud free tier (Oracle Linux, aarch64), Ubuntu, Debian, Fedora. Use when someone says "set up a kannaka server", "provision a node", "here is my server, make it a kannaka node", or asks how to install kannaka on a VPS.
Hand a fresh Linux server to an AI and get back a running Kannaka node.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 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
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-pipe-to-shellscripts/provision.sh:121Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)as_user "curl -fsSL '$INSTALL_URL' | sh -s -- $flags" || { echo "installer failed" >&2; return 1; }code literal -
medium Dangerous commands
cmd-privilegescripts/provision.sh:284Privilege escalation / world-writable permissions[ -f "$SYS_BIN" ] && $SUDO mv "$SYS_BIN" "$SYS_BIN.previous" # never overwrite a running binary in place
-
medium Dangerous commands
cmd-privilegescripts/provision.sh:289Privilege escalation / world-writable permissionsprintf '%s\n' "$runner_body" | $SUDO tee "$RUNNER" >/dev/null && $SUDO chmod 755 "$RUNNER"
-
medium Dangerous commands
cmd-privilegescripts/provision.sh:290Privilege escalation / world-writable permissionsprintf '%s\n' "$unit_node" | $SUDO tee "$UNIT_NODE" >/dev/null
-
medium Dangerous commands
cmd-privilegescripts/provision.sh:291Privilege escalation / world-writable permissionsif [ "$ROLE" = serve ]; then printf '%s\n' "$unit_serve" | $SUDO tee "$UNIT_SERVE" >/dev/null; fi
-
medium Dangerous commands
cmd-privilegescripts/provision.sh:292Privilege escalation / world-writable permissionsif [ "$DREAM" = true ]; then printf '%s\n' "$unit_dream" | $SUDO tee "$UNIT_DREAM" >/dev/null; printf '%s\n' "$timer_dream" | $SUDO tee "$TIMER_DREAM" >/dev/null; fi
-
low Dangerous commands
cmd-background-processscripts/provision.sh:294Starts a background / autostarted process$SUDO systemctl enable --now kannaka-node.service >/dev/null 2>&1 || $SUDO systemctl restart kannaka-node.service
-
low Dangerous commands
cmd-background-processscripts/provision.sh:297Starts a background / autostarted process[ "$ROLE" = serve ] && $SUDO systemctl enable --now kannaka-serve.service >/dev/null 2>&1
-
low Dangerous commands
cmd-background-processscripts/provision.sh:298Starts a background / autostarted process[ "$DREAM" = true ] && $SUDO systemctl enable --now kannaka-dream.timer >/dev/null 2>&1
-
low Dangerous commands
cmd-privilegeSKILL.md:67Privilege escalation / world-writable permissions (quoted — discussed, not commanded)**4. Service.** `sudo bash provision.sh service [--role serve] [--no-dream]`. This is the
quoted -
low Dangerous commands
cmd-privilegeSKILL.md:115Privilege escalation / world-writable permissions (documentation table row)| `status=127` restart loop | the runner script is missing | `sudo bash provision.sh service` rewrites it |
table -
low Dangerous commands
cmd-privilegeSKILL.md:122Privilege escalation / world-writable permissions (quoted — discussed, not commanded)(manifest-pinned, sha2…ied) followed by `sudo bash provision.sh service`, which swaps
quoted
Files scanned: 5. 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 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2162 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 596: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 6 items
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.