FC signaai
Send payments, messages, escrow, and verifiable outputs between AI agents on the Signum blockchain. Use when asked about agent-to-agent payments, on-chain messages, escrow tasks, verifying AI output, or checking wallet balances. Also use when running multi-agent demos or when one OpenClaw needs to interact with another.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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-persistencesetup.sh:180Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load "$PLIST_FILE"
-
high Dangerous commands
cmd-persistenceSKILL.md:380Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/io.signaai.listener.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:383Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/io.signaai.listener.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:386Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/io.signaai.listener.plist && \
-
high Dangerous commands
cmd-persistenceSKILL.md:387Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/io.signaai.listener.plist
Medium and low: 4
-
medium Broad scope
meta-agent-memory-dumpmemory/tasks.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensmemory/tasks.md
-
medium Exfiltration
exfil-webhook-urlscripts/escrow.py:219Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{token}/sendMessage"quoted -
medium Exfiltration
exfil-webhook-urlscripts/listener.py:797Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)url = f"https://api.telegram.org/bot{token}/sendMessage"quoted -
medium Dangerous commands
cmd-persistencesetup.sh:14Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)PLIST_FILE="$HOME/Library/LaunchAgents/io.signaai.listener.plist"
code literal
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5133 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 55/100
- 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 (signaai) differs from the folder (signa-ai)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5133 tokens
- 100Steps. 24 steps
- 100Failures and branches. 15 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -225 emoji in the instructions: noise for the model
- -35 of 11 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 321: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (38 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.