mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-23 06:59:28 +00:00
Marius CiepluchandClaude Fable 5.1
69b5e0efcc
Maintainer decision 2026-10-02 (no symlink). AGENTS.md, README, the two spec docs, the kiro-spec-batch skill and the provenance ignore list are repointed; the OpenCode plugin package.json stays under .opencode. Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo
1.3 KiB
1.3 KiB
name, description
| name | description |
|---|---|
| openultrasast-triage | OpenUltraSAST false-positive elimination, ranking calibration, evidence ladder, verifier triage, and finding adjudication. Use when reviewing findings, reducing false positives, or deciding whether evidence is enough. |
OpenUltraSAST Triage
Use this skill when triaging OpenUltraSAST findings from opencode.
Triage Loop
- Identify the finding, path, rule, severity, confidence, and evidence level.
- Separate deterministic evidence from model assumptions.
- Check attacker control, reachability, sanitizer behavior, duplicates, impact, and contradictory evidence.
- If rejected or unresolved, record the false-positive reason and scope.
- Prefer scoped demotion over deleting a vulnerability class globally.
- Feed the outcome into ranking calibration and prompt constraints.
False-Positive Reasons
unreachable_pathmissing_attacker_controlsanitizer_disprovedstatic_rule_mismatchincorrect_model_assumptionduplicateinsufficient_impactunsupportedcontradictedunverified
Decision Standard
If evidence is uncertain, mark the finding as requiring next evidence instead of escalating severity. Difficult or high-impact disagreements should trigger fusion/deeper reasoning when available.