mitigation-dot-team/MergeShield - PR Risk Analysis

Calculates a risk score (0-10) for each PR using heuristics + LLM. Risk visibility for CTOs.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
mergeshield-api-keyMergeShield API key for plan validation and account association. Get yours at https://mitigation.teamyes
github-tokenGitHub token to access the API (pull requests, comments)yes
llm-providerLLM provider: openai (Starter+Premium), claude, azure, gemini (Premium only). Default: claudenoclaude
llm-api-keyAPI key for the selected LLM provider (optional)no""
llm-modelModel to use. Default: gpt-4o-mini (OpenAI), claude-3-5-sonnet-20241022 (Claude), gpt-4o-mini (Azure), gemini-1.5-flash (Gemini)no""
enable-llmEnable contextual LLM analysis (requires llm-api-key)nofalse
risk-thresholdMinimum score to fail the check (0-10). Default: 7no7
webhook-urlWebhook URL to send analysis results to (optional)no""
webhook-secretHMAC secret to sign the webhook payload (optional but recommended)no""
internal-reporter-urlMergeShield internal system URL to report analysis results (optional)no""
internal-reporter-secretHMAC secret to authenticate with the internal system (optional but recommended)no""
comment-languageLanguage for the PR comment: en (English) or es (Spanish). Default: ennoen
namedescription
risk-scoreFinal risk score (0-10)
risk-levelRisk level: low, medium, high
heuristic-scoreHeuristic analysis score (0-10)
llm-scoreLLM analysis score (0-10), empty if LLM is disabled
llm-justificationLLM justification