Passed 20 of 22 test cases with the skill, and 19 of 22 without it.
Without skill86%
With skill91%
Checks it passed that the model alone missed
Calculates a target score of 6 points out of 10.
Attributes 2 points for TVL exceeding 10M dollars.
Attributes 2 points for Immunefi critical bounty exceeding 50K dollars.
and 4 more in the full report
2 fixed18 passed either way1 still failing1 broke
Pass-rate lift
+5 pp
Tokens
+262%
Agent turns
0%
Response time
-8%
Model gemini-3.6-flashMeasured 8/10/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
I am looking at a smart contract bug bounty target with $15 million in TVL, a $60K top critical bounty on Immunefi, deployed 20 days ago, full source code with natspec comments, but it was previously audited by Halborn on its current version. Run these project details through your pre-dive evaluation framework and target scoring method, and present the calculated score along with a clear go/no-go recommendation.
What was checked, without and with the skill
Checked
Without skill
With skill
Calculates a target score of 6 points out of 10.
Missed
Passed
Attributes 2 points for TVL exceeding 10M dollars.
Missed
Passed
Attributes 2 points for Immunefi critical bounty exceeding 50K dollars.
Missed
Passed
Recommends proceeding with the audit target based on reaching the score threshold.
Missed
Passed
case-01 · gemini-3.6-flash · 8/10/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
Soft kill: OZ/ToB/Cyfrin audit on current version + codebase > 500K LOC → expect 40+ hours for maybe 1 finding. Only proceed if bounty floor > $50K AND you have protocol-specific expertise.
Target scoring (go if >= 6/10):
TVL > $10M: +2
Immunefi program with Critical >= $50K: +2
No top-tier audit on current version: +2
< 30 days since deploy: +1
Protocol you've hunted before: +1
Source code + natspec comments: +1
Upgradeable proxies: +1
THE ONE RULE
"Read ALL sibling functions. If vote() has a modifier, check poke(), reset(), harvest(). The missing modifier on the sibling IS the bug."
This single rule explains 19% of all Critical findings.
1. ACCOUNTING STATE DESYNCHRONIZATION
#1 Critical bug class — 28% of all Criticals on Immunefi.