CC investigation-report
One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot, lp-lock) into one verdict. Keyless core.
One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Exfiltration
net-credential-useSKILL.md:55Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)# ./secretcurl substitutes {ETHERSCAN_API_KEY} internally, so no `$SECRET` hits thesecurity skill -
low Exfiltration
net-credential-useSKILL.md:59Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=…&action=…&address=…" | jq '.result[0]'
security skill -
low Exfiltration
net-credential-useSKILL.md:86Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=token&action=…&contractaddress=…&page=1&offset=…" | jq '.result'
security skill -
low Exfiltration
net-credential-useSKILL.md:111Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)./secretcurl -m 10 -s "https://api.etherscan.io/v2/api?chainid=8453&module=…&action=…&address=…" | jq '.result[0] | {ContractName, Proxy, Implementation, CompilerVersiosecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 1. 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 ≈ 6913 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6913 tokens
- 100Steps. 35 steps
- 100Failures and branches. 5 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
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +3Description length 198: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.