FB lattice-protocol
(no description)
Not recommendedcritical or high security findings · low grade F
As a process B 65/100 · Nearly there — 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.
Dangerous commands
If you install
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.
For the author
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.
- Add a description to the frontmatter: without it the skill never triggers.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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 · 13
-
high Dangerous commands
cmd-persistencescripts/configure.sh:96Persistence mechanism (cron / launchd / scheduled task / autorun registry)EXISTING_CRONTAB=$(crontab -l 2>/dev/null || true)
-
high Dangerous commands
cmd-persistencescripts/configure.sh:111Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "$NEW_CRONTAB" | crontab -
-
high Dangerous commands
cmd-persistencescripts/configure.sh:124Persistence mechanism (cron / launchd / scheduled task / autorun registry)EXISTING_CRONTAB=$(crontab -l 2>/dev/null || true)
-
high Dangerous commands
cmd-persistencescripts/configure.sh:126Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "$FILTERED_CRONTAB" | crontab -
Medium and low: 9
-
medium Dangerous commands
cmd-persistenceSKILL.md:178Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l | grep -v "lattice-" | crontab -
detector -
low Exfiltration
net-credential-usebin/lattice-attest.js:56Credential used in a network call (verify the destination is the intended service) (test fixture / example file)const response = await fetch(`${LATTICE_URL}/api/v1/exp/${keys.did}`);fixture -
low Dangerous commands
cmd-cron-mentionscripts/configure.sh:96Mentions editing / listing crontabEXISTING_CRONTAB=$(crontab -l 2>/dev/null || true)
-
low Dangerous commands
cmd-cron-mentionscripts/configure.sh:116Mentions editing / listing crontab (string literal in code, not executed)print_info "To view your cron jobs: crontab -l"
code literal -
low Dangerous commands
cmd-cron-mentionscripts/configure.sh:117Mentions editing / listing crontab (detector / deny-list definition; string literal in code, not executed)print_info "To remove all lattice cron jobs: crontab -l | grep -v lattice- | crontab -"
detectorcode literal -
low Dangerous commands
cmd-cron-mentionscripts/configure.sh:124Mentions editing / listing crontabEXISTING_CRONTAB=$(crontab -l 2>/dev/null || true)
-
low Dangerous commands
cmd-cron-mentionscripts/configure.sh:172Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "lattice-"; then
-
low Dangerous commands
cmd-cron-mentionskill-card.md:23Mentions editing / listing crontabMitigation: Choose no in the configuration wizard for manual-only use; if automation is enabled, review crontab -l and ~/.lattice/logs periodically. <br>
-
low Dangerous commands
cmd-cron-mentionSKILL.md:178Mentions editing / listing crontabcrontab -l | grep -v "lattice-" | crontab -
Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger - warning
body-longSKILL.md body ≈ 5448 tokens (recommended < 5000); move details to references/
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
- 30When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5448 tokens
- 100Tools and files. No external tools needed
- 100Steps. 115 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 17 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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 63 headings
- +3Step-by-step instructions: 115 items
- +4Has examples (21 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.
External checks
ClawHub: clean
This skill is a disclosed Lattice social-network CLI with optional scheduled read-only monitoring, but users should notice the local key file and cron option before enabling it.
LLM: benign (high) · VirusTotal: suspicious · 28 May 2026