fix(daily-vulnhunter-scan): raise max-ai-credits to 1500 - #47236
Merged
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Update max AI credits in Daily VulnHunter scan workflow
fix(daily-vulnhunter-scan): raise max-ai-credits to 1500
Jul 22, 2026
Collaborator
|
@copilot do not raise AIC, change the agent prompt / strategy to focus on a subset of the issues found and stay within budget |
Contributor
Author
Got it — reverting the AIC increase and refocusing the prompt to scope the scan to a prioritized subset so it stays within the 1K budget. |
…y points Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Intended to prevent VulnHunter scans from exceeding the 1K AI-credit guardrail, but the limit remains unchanged while scan coverage is reduced.
Changes:
- Limits VulnHunter to two phases and selected entry points.
- Reduces maximum reported findings from five to three.
- Updates generated workflow metadata only.
Show a summary per file
| File | Description |
|---|---|
.github/workflows/daily-vulnhunter-scan.md |
Narrows the scan methodology and reporting. |
.github/workflows/daily-vulnhunter-scan.lock.yml |
Updates the body hash; retains the 1K default limit. |
Review details
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 2/2 changed files
- Comments generated: 2
- Review effort level: Medium
| @@ -1,4 +1,4 @@ | |||
| # gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"5f7e1cd29e3ca0e84205de47c594770818b70d9a9a9689b6685193ce970306b2","body_hash":"a48dbec98bfea6f55c1ae6e80414c0759b46e692b7c5712b5c122f80dd909fcd","strict":true,"agent_id":"claude","agent_model":"claude-sonnet-4.6","engine_versions":{"claude":"2.1.216"}} | |||
| # gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"5f7e1cd29e3ca0e84205de47c594770818b70d9a9a9689b6685193ce970306b2","body_hash":"25bdc06d98c7da8265c15256225306a4fdfdc0c1d8792e15f368bb8ba112517e","strict":true,"agent_id":"claude","agent_model":"claude-sonnet-4.6","engine_versions":{"claude":"2.1.216"}} | |||
| - every file under `/tmp/gh-aw/agent/vulnhunter/vulnhunter/vulnhunt/phases/` | ||
| 3. Follow the extracted `vulnhunt` instructions as your operating playbook and scan `/tmp/gh-aw/agent/vulnhunter/repo` for verified, exploitable vulnerabilities. | ||
| 4. Save your intermediate notes and any machine-readable findings under `/tmp/gh-aw/agent/vulnhunter/out/`. | ||
| - List the files under `/tmp/gh-aw/agent/vulnhunter/vulnhunter/vulnhunt/phases/` and select **at most 2 phases** most applicable to a Go CLI codebase (e.g. injection, secrets). Read only those phase files. |
Contributor
|
🎉 This pull request is included in a new release. Release: |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The Daily VulnHunter Scan was hitting the default 1K AIC guardrail — the scan legitimately consumed ~1029 AIC (57 turns, 62 reads, 41 greps) running the full multi-phase VulnHunter methodology across the repo.
Changes
daily-vulnhunter-scan.md— addsmax-ai-credits: 1500, giving ~50% headroom above observed usagedaily-vulnhunter-scan.lock.yml— recompiled; firewall config updated to"maxAiCredits": 1500