BC aiusd-skill
AIUSD trading and account management skill for cryptocurrency trading and account management.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Obfuscation
obf-base64-blobaiusd-skill-installer.sh:112Long base64-looking blobH4sI…kAA+y923…Qyk/Zt91Wmf9B7/cDOJ+hc3D…v24+/Hjx4…RTT+NRmN…zxX+2Wgt
-
low Obfuscation
obf-base64-blobaiusd-skill-installer.js:91Long base64-looking blob (quoted — discussed, not commanded)const PACKAGE_DATA = `H4sI…kAA+y923…Qyk/Zt91Wmf9B7/cDOJ+hc3D…v24+/Hjx4…nwP
quoted -
low Secrets in code
secret-high-entropy-tokenaiusd-skill-installer.js:91High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const PACKAGE_DATA = `H4sI…kAA+y923…Qyk/Zt91Wmf9B7/cDOJ+hc3D…v24+/Hjx4…nwP
quoted -
low Secrets in code
secret-high-entropy-tokenaiusd-skill-installer.sh:112High-entropy token-like string (may be an id, hash or a credential)H4sI…kAA+y923…Qyk/Zt91Wmf9B7/cDOJ+hc3D…v24+/Hjx4…RTT+NRmN…zxX+2Wgt
Files scanned: 6. 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 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 (aiusd-skill) differs from the folder (aiusd-skill-agent)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4312 tokens
- 100Steps. 129 steps
- 100Failures and branches. 4 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 The response is described with custom markup (5 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 93: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 43 headings
- +3Step-by-step instructions: 129 items
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.