Ouros-App/ouros-skills / skills/finding-verifier
finding-verifier
VerifiedIndependently verify a suspected Ouros security finding. Use after another agent reports a vulnerability or suspicious behavior, before severity is finalized, an issue is opened, or a fix is proposed as security-critical.
Finding Verifier
Assume the candidate finding may be wrong. Disprove it first; confirm it only if evidence survives independent checking.
Inputs
Require enough information to identify affected component, claimed security boundary, prerequisites, and candidate reproduction/evidence.
If runtime reproduction is needed, use ../safe-runtime-testing/SKILL.md.
Verification procedure
- State the claim narrowly. Convert broad language into one falsifiable sentence.
- Check the boundary. Identify what should be prevented and where enforcement is expected.
- Inspect code/config independently. Do not rely on the original agent's interpretation.
- Try to falsify. Look for upstream/downstream checks, fixtures, mocks, environment-only shortcuts, or expected behavior.
- Reproduce minimally when authorized. Use independent inputs or a fresh fixture.
- Classify.
Use confirmed when a boundary violation is reproduced or deterministically demonstrated; rejected for expected behavior/test artifacts; blocked when scope/access is insufficient.
Severity discipline
Base severity on privileges required, reachable data/actions, cross-user/tenant reach, repeatability, user interaction, blast radius, and compensating controls. If impact is uncertain, say so.
Confirmed finding format
Include: ID, status, component, boundary, prerequisites, minimal_reproduction, expected, observed, impact, root_cause, severity_rationale, evidence, cleanup, regression_test, and remediation_direction.
Redact secrets and unnecessary personal data. Do not silently fix the bug before preserving sufficient evidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |