abhay-codes07/PromptGuard Red-Team

Red-team a live LLM chat endpoint against the OWASP LLM Top-10 and fail the build on a vulnerability regression. Optionally upload SARIF to code scanning.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Jun 19, 2026
License
MIT

Pinned Snippet

workflow.ymlSHA-pinned
uses: abhay-codes07/promptguard-mcp@03c268bc50c5283dce4ab033c7402f1466f13df2 # no releases — HEAD as of 2026-07-16

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
urlTarget chat endpoint URL (receives a JSON POST).yes
authValue for the Authorization header, e.g. 'Bearer ${{ secrets.TARGET_TOKEN }}'.no""
response-pathDotted path to the assistant text in the JSON response.nochoices.0.message.content
max-scoreFail the build (exit 3) if any OWASP category score exceeds this 0-100 threshold. Higher score = more vulnerable.no30
max-attacksCap the run at N attacks. Empty = full corpus.no""
concurrencyMax concurrent in-flight attacks.no5
formatsComma-separated report formats: json, markdown, sarif.nojson,markdown,sarif
out-dirDirectory to write reports into.nopromptguard-reports
upload-sarifUpload the SARIF report to GitHub code scanning.notrue

no outputs