FC muster
Install and work within a Muster co-working space. Tell your agent 'Install Muster' — it handles everything. Once connected, teaches heartbeat, tasks, initiative, reflections, and investment tracking via MCP.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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.
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
- 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 · 9
-
high Dangerous commands
cmd-pipe-to-shellscripts/install.sh:128Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://get.docker.com | sh
-
high Dangerous commands
cmd-persistencescripts/install.sh:285Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl bootstrap "gui/$(id -u)" "$PLIST_PATH"
-
high Dangerous commands
cmd-persistencescripts/install.sh:366Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl bootstrap "gui/$(id -u)" "$TUNNEL_PLIST"
Medium and low: 6
-
medium Exfiltration
exfil-webhook-urlREFERENCE.md:44Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded){"tunnel_url": "https://random-words.trycloudflare.com", "updated_at": "2026…..."}quoted -
medium Dangerous commands
cmd-persistencescripts/install.sh:233Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST_PATH="$HOME/Library/LaunchAgents/${SERVICE_LABEL}.plist"code literal -
medium Dangerous commands
cmd-persistencescripts/install.sh:329Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)TUNNEL_PLIST="$HOME/Library/LaunchAgents/${TUNNEL_LABEL}.plist"code literal -
medium Dangerous commands
cmd-persistencescripts/uninstall.sh:92Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST="$HOME/Library/LaunchAgents/${label}.plist"code literal -
medium Dangerous commands
cmd-pipe-to-shellTROUBLESHOOTING.md:8Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**Linux:** `curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker $USER`
quoted -
medium Dangerous commands
cmd-persistenceTROUBLESHOOTING.md:80Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)`launchctl bootstrap "gui/$(id -u)" ~/Library/LaunchAgents/com.bai.muster.plist`
quoted
Files scanned: 10. 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")
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1660 tokens
- 100Progress reporting. Reports progress
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 208: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 51 items
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.