Use when designing or auditing ACM CCS experiments, attack demonstrations, adaptive-attack defense evaluations, security measurements, baselines, overhead and cost reporting, ablations, and claim-to-evidence fit, with emphasis on evidence that survives an adversarial program committee rather than leaderboard wins.
SkillScore83Maintained
Automatic
◆Security & AppSec pack
Last verified 8/15/2026
What it changes
Passed 19 of 23 test cases with the skill, and 15 of 23 without it.
Without skill65%
With skill83%
Checks it passed that the model alone missed
Highlights the lack of state-of-the-art attack baselines.
Recommends evaluating against targets with active power-analysis countermeasures.
Notes the absence of gas cost overhead measurements on standard high-frequency contracts.
and 1 more in the full report
4 fixed15 passed either way4 still failing0 broke
Pass-rate lift
+17 pp
Tokens
-13%
Agent turns
0%
Response time
-47%
Model gemini-3.6-flashMeasured 8/15/2026v119 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
We are wrapping up an attack paper draft targeting SGX enclaves to submit to ACM CCS. We demonstrated a cache side-channel extraction against an open-source cryptographic library running inside Gramine-SGX v1.4, recording trace collection times and query budgets. Please review our current experiment package. We need an assessment that covers our readiness level, pairs each security assertion with its supporting evaluation artifact, flags any absent security evidence (such as missing baseline comparisons or adaptive counter-strategies), identifies gaps where our test environment violates our threat model, and recommends one top-priority experiment run to execute before submission.
What was checked, without and with the skill
Checked
Without skill
With skill
Highlights the lack of state-of-the-art attack baselines.
Missed
Passed
case-02 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md63 linessingle file
CCS Experiments
Use this before submission when the attack demonstration, defense evaluation, or measurement
story is not yet locked.
Experiment audit
Map each security claim to a specific artifact: an exploit run, an overhead measurement, a
coverage number, a false-positive/false-negative table, or a measurement dataset.
For attacks, demonstrate the exploit against a realistic, named target (software version,
platform, configuration) and report the resource cost to the attacker.
For defenses, evaluate against an adaptive attacker built with knowledge of the defense,
and report performance overhead, memory cost, and any compatibility breakage.
For measurements, validate sampling: document the population, the vantage point, coverage
and blind spots, and ground-truth checks against known cases.
Include baselines that represent the state of the art in attack or defense, not strawmen.
Report variance for stochastic results and audit for leakage, selection bias, and any
mismatch between the threat model and the tested configuration.
What experiments are for at this venue
CCS experiments exist to make a security claim undeniable to a skeptic, not to top a
benchmark. One clean end-to-end exploit against a real target outweighs a table of
micro-benchmarks.
The strongest defense design triad: the attack it stops, an adaptive attack that knows the
defense, and a deployment-cost measurement. Missing the middle element is the classic CCS
defense reject.
Reviewers, often practitioners, check whether the evaluation environment matches the threat
model. A defense claimed for production but tested only on a toy in a lab invites the
relevance question.
Attack-and-defense evaluation table
Security claim
Matching evidence
Reject pattern avoided
Exploit is practical
End-to-end run on named target with attacker cost
"Works only in a lab against a strawman"
Defense stops the attack
Detection/prevention rate on the original attack
"No numbers, only a design argument"
Defense resists adaptation
Adaptive attacker with defense knowledge, degraded results
"Only the non-adaptive attack was tried"
Deployment is feasible
Overhead, memory, compatibility on a realistic workload