Communicating with triage
SkillAI & modelsWork productively with triagers after you submit, answer follow-ups, and handle duplicate, not-applicable, or severity disputes professionally. Load on "triage asked for more info", "they closed it as N/A", "dispute the severity/duplicate", or managing a report thread. Signals: a submitted report awaiting/receiving triage, a disagreement on outcome.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Communicating with triage skill
What this skill tells your AI
The instructions your AI receives, as published by noorqureshi/sploitagent in skills/reporting/reporting-triage-communication/SKILL.md and read by ahel’s review.
When it applies
The report is in and now it's a conversation. How you handle triage largely decides the outcome — a valid bug can be closed over a bad thread, and a borderline one can be paid with a clear, calm one.
Why it works
Triagers process a queue under time pressure and act on what's in front of them. A report that reproduces from the steps alone, and follow-ups that answer the exact question with evidence, remove every reason to close it — while professionalism keeps the relationship (and your reputation) intact.
Method
- Pre-empt questions in the report: exact requests/responses, account roles, a clean-session repro, and a crisp impact statement — most "need more info" rounds are avoidable.
- When asked for more: give precisely what's requested (a fresh repro, a video, the missing header), not a wall of text. Re-confirm from a clean state.
- Duplicate: ask politely for the dupe reference and compare — if yours is genuinely distinct (different root cause, endpoint, or a working chain where the original was theoretical), lay out the difference factually. If it's truly the same, accept it and move on.
- Not applicable / won't fix: restate the demonstrated impact and, if needed, escalate the PoC to show real consequence (stay in scope). Don't argue theory — show it.
- Severity dispute: bring the CVSS vector and the program's own scale (
reporting-cvss-scoring), and justify the contested metric with what you proved. - Escalate correctly: use the platform's mediation/escalation path when stuck; keep it factual.
Gotchas
- Never threaten public disclosure or go around the process — it voids safe harbor and burns you.
- Tone is leverage: rude threads get minimal effort; respectful, evidence-first threads get benefit of the doubt.
- Don't keep pushing a genuine dupe or a truly out-of-scope report — it costs goodwill you'll need later.
Verify success
The thread moves toward resolution on the merits: your follow-ups answered the actual question with evidence, and any dispute is argued from demonstrated impact and the program's own policy.
References
Platform mediation/disclosure guidelines; the reporting-bug-bounty-writeup, reporting-cvss-scoring,
and tradecraft-bugbounty-platforms skills.
Signals
- GitHub stars
- 20
- Forks
- 7
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
reporting-triage-communication- Source
- github.com/noorqureshi/sploitagent
github.com/noorqureshi/sploitagent
Related picks
Skill · mukul975
The pick for Vulnerabilitiescode-quality-analyzer
Skill · alibaba
The pick for Vulnerabilitiesskill-creator
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & models