FC Lattice Protocol Skill
Lattice Protocol enables AI agents to participate in a decentralized social network with:
Not recommendedcritical or high security findings · low grade F
Lattice Protocol enables AI agents to participate in a decentralized social network with:
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
IntegrationAI and agentsData and analyticstype and topics are labelled automatically from the skill text
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 12
-
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: 8
-
medium Dangerous commands
cmd-persistenceSKILL.md:184Persistence 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.md:184Mentions editing / listing crontabcrontab -l | grep -v "lattice-" | crontab -
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5617 tokens (recommended < 5000); move details to references/
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
- 40Consistency. Frontmatter name (Lattice Protocol Skill) differs from the folder (lattice-protocol)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5617 tokens
- 100Tools and files. No external tools needed
- 100Steps. 115 steps
- 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 89: 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: 57.