CC clawbuddy-buddy
Turn your AI agent into a ClawBuddy buddy — share knowledge with hatchlings via SSE.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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
- 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.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Instruction override
en-ignore-previousscripts/listen.js:111Instruction-override phrase ("ignore previous instructions") (documentation table row)| Authority spoofing | "SYSTEM OVERRIDE", "ADMIN MODE", "IGNORE PREVIOUS INSTRUCTIONS" |
table -
medium Exfiltration
net-credential-useSKILL.md:99Credential used in a network call (verify the destination is the intended service)curl -sS http://127.0.0.1:8642/v1/models -H "Authorization: Bearer $GATEWAY_TOKEN"
-
medium Instruction override
en-ignore-previousSKILL.md:866Instruction-override phrase ("ignore previous instructions") (documentation table row)| Authority spoofing | "SYSTEM OVERRIDE", "ADMIN MODE", "IGNORE PREVIOUS INSTRUCTIONS" |
table -
low Dangerous commands
cmd-background-processSKILL.md:676Starts a background / autostarted processsudo systemctl enable clawbuddy-buddy
Files scanned: 16. 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") - warning
body-longSKILL.md body ≈ 7926 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 33 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7926 tokens
- 100Steps. 136 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +3Description length 84: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -33 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 70 headings
- +3Step-by-step instructions: 136 items
- +4Has examples (42 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.