Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →transilienceai/regression-sweep
Re-validates every previously-confirmed finding against its current target — detects drift (patched, mitigated, re-introduced). Cron-driven weekly sweep across the org's validated finding tree.
Passed 12 of 18 test cases with the skill, and 4 of 18 without it.
and 8 more in the full report
11 fixed4 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What default automated execution schedule and UTC timing is specified for recurring sweep passes?
| Checked | Without skill | With skill |
|---|---|---|
| Schedules execution weekly on Mondays at 02:00 UTC. | Missed | Passed |
The instructions your model reads when the skill loads.
Walk the entire validated/*.json tree, re-fire each finding's poc.py, compare output against the recorded poc_output.txt, and write a weekly drift report. Mounted onto the cloud-agent task #4.
Cron weekly (default Mondays 02:00 UTC). May also be invoked ad-hoc after a major patch deployment.
validated/*.json and resolve each entry's FINDING_DIR (under findings/finding-NNN/).python3 poc.py with a 60-second timeout.findings/finding-NNN/evidence/validation/regression-{week}-rerun.txt.findings/finding-NNN/evidence/validation/poc-rerun-output.txt (the validator's original re-run output) using a normalized line-set comparison (strip timestamps, request IDs, ephemeral tokens).tools/nvd-lookup.py — has severity changed?still_valid — re-run matches baseline within tolerance, CVSS unchanged.drift_severity — re-run matches, but CVSS shifted ≥1.0 (NVD re-scored).newly_invalid — re-run output diverges, exploit no longer fires. Likely patched.newly_revalidated — finding had been marked REJECTED later, but now fires again. Regression.inconclusive — re-run errored (network, target unreachable). Retry next sweep.artifacts/regression-{YYYYWww}.json + human-readable regression-{YYYYWww}.md. Transitions (newly_revalidated, drift_severity, newly_invalid) appear in the report under explicit headers for analyst review.{OUTPUT_DIR}/
artifacts/
regression-{YYYYWww}.json # machine-readable result
regression-{YYYYWww}.md # human summary
findings/finding-NNN/evidence/validation/
regression-{YYYYWww}-rerun.txt # captured re-run output
regression-{week}.json schema:
{
"week": "2026W19",
test cases passed, vs 4 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.