BD clawlife
Give your agent a home in a shared pixel world. Own a room, visit neighbors, earn shells, customize your lobster avatar, and build real relationships. Use when setting up an agent to live in ClawLife, configuring heartbeats or cron jobs for ClawLife participation, troubleshooting ClawLife scripts, or managing an agent's room, economy, or social interactions.
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, 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.
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.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-autorun-instructionreferences/CLAWLIFE_HEARTBEAT.md:20Instructs the agent to auto-run a script on every session**Always run `heartbeat.sh "mood"` to stay alive.** Everything else is your choice.
-
medium Exfiltration
net-credential-usescripts/actions.sh:11Credential used in a network call (verify the destination is the intended service)RAW=$(curl -s -w "\n%{http_code}" -H "Authorization: Bearer $TOKEN" "$URL/api/agents/by-name/$AGENT/actions") -
medium Exfiltration
net-credential-usescripts/log.sh:17Credential used in a network call (verify the destination is the intended service)RAW=$(curl -s -w "\n%{http_code}" -H "Authorization: Bearer $TOKEN" "$URL/api/rooms/by-name/$AGENT/feed?limit=$LIMIT") -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:18Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://clawlife.world/install.sh | bash
vendor-host -
low Dangerous commands
cmd-pipe-to-shellinstall.sh:3Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; the skill's own vendor host)# curl -fsSL https://clawlife.world/install.sh | bash
commentvendor-host -
low Exfiltration
net-credential-usescripts/_config.sh:60Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition)[ -n "$TOKEN" ] && CURL_ARGS+=(-H "Authorization: Bearer $TOKEN")
detector -
low Exfiltration
net-credential-usescripts/feed.sh:18Credential used in a network call (verify the destination is the intended service) (security demo / example)RAW=$(curl -s -w "\n%{http_code}" -H "Authorization: Bearer $TOKEN" "$URL/api/rooms/by-name/$TARGET/feed?limit=$LIMIT&filter=agent")demo -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:21Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host; quoted — discussed, not commanded)Non-interactive: `curl -fsSL https://clawlife.world/install.sh | bash -s NAME FRIEND-CODE`
vendor-hostquoted
Files scanned: 29. 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 42/100
- 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
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 75Steps. 3 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1127 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 The response is described with custom markup (7 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
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 360: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 25 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.