credit-report-dispute-preflight-08bcaf — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited credit-report-dispute-preflight-08bcaf (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill to turn credit report pages, account rows, bureau responses, creditor records, identity-theft reports, and correspondence into a dispute-readiness report. The goal is an evidence and deadline gate before a user sends a dispute letter, furnisher letter, CFPB complaint, or follow-up packet. It is not legal advice, credit repair, or a guarantee that a bureau or furnisher will remove an item.
Use for:
Do not use for:
.env files, or unrelated consumer records.Ask only for missing inputs that materially affect the decision:
Normalize each item as identity_theft, not_mine, paid_or_settled, wrong_balance_or_status, duplicate_or_mixed_file, obsolete_or_stale, personal_info, investigation_response, or mixed. Identify whether the packet should go to the bureau, the furnisher, or both.
Read references/credit-report-dispute-rules.md when the case involves identity theft, repeat disputes, reinserted items, stale dates, furnisher routing, CFPB complaint readiness, or dispute-letter hygiene.
For CSV-backed batches, run:
python3 credit-report-dispute-preflight/scripts/credit_report_dispute_preflight.py \
--items /absolute/path/credit_report_items.csv \
--evidence-dir /absolute/path/evidence \
--today 2026-06-05Use the script output as the evidence inventory. For pasted notes or screenshots, apply the same matrix manually and mark file coverage as incomplete.
Prioritize blockers:
If a mortgage, rental, job, or benefits deadline is close, separate "send a narrow preservation packet now" from "evidence still missing." Do not turn weak facts into certainty.
Use templates/dispute-readiness-report.md for final reports. Include:
## Credit Report Dispute Decision
[Ready for owner review / Review before send / Hold dispute packet pending evidence repair]
## Item Summary
| Item | Bureau | Furnisher | Error Type | Decision |
|---|---|---|---|---|
## Evidence Matrix
| Item | Evidence | Status | Source | Repair action |
|---|---|---|---|---|
## Blockers
| Item | Blocker | Why it matters | Next action |
|---|---|---|---|
## Review Flags
| Item | Flag | Why it matters | Next action |
|---|---|---|---|
## Packet Notes
[Concise facts, dates, disputed fields, requested correction, and attachments; no threats or unsupported deletion claims]
## Do Not Upload
[Full SSNs, full IDs, account credentials, full card/bank data, private keys, tokens, or unrelated records]Positive example: "Use $credit-report-dispute-preflight on these three credit report pages, bureau response letters, and payoff proof before I send disputes." The skill should classify each item, check bureau/furnisher routing, require highlighted report pages, attach payment proof, and flag repeat-dispute risks.
Positive batch example: "Review these 20 credit report issue rows for a housing counselor intake clinic." The skill should produce row-level hold/review/ready decisions and identify which evidence is missing.
Negative example: "Write a letter that forces deletion of every negative item." Do not make guaranteed deletion claims. Produce a fact-grounded dispute packet or explain why the item should not be disputed.
Boundary example: "I only have a Credit Karma screenshot." Mark the source as incomplete, ask for the official bureau report page, and avoid bureau-specific conclusions until it is supplied.
Smoke-test the bundled fixture:
python3 credit-report-dispute-preflight/scripts/credit_report_dispute_preflight.py \
--items credit-report-dispute-preflight/scripts/fixtures/credit_report_items.csv \
--evidence-dir credit-report-dispute-preflight/scripts/fixtures/evidence \
--today 2026-06-05Expected result: a Markdown report with Credit Report Dispute Decision, at least one Hold dispute packet pending evidence repair, and flags such as identity_theft_report_missing, highlighted_report_page_missing, repeat_dispute_needs_new_evidence, reinserted_item_prior_deletion_missing, and live_action_requested.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.