reyracom/NIfra AI Security Scan

Automated exploit simulation, attack surface mapping & pipeline protection for LLM apps and AI agents. Detects prompt injection, RAG poisoning, tool abuse, excessive agency, and supply chain vulnerabilities.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Mar 16, 2026
License
None

Pinned Snippet

workflow.ymlSHA-pinned
uses: reyracom/nifra-agent@579d18c470c1a442024b73df28afa4dd7f3b02a9 # v0.2.0

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

namedescriptionrequireddefault
targetPath to the AI application directory to scan (relative to workspace root)no.
fail-onExit with error code if findings at this severity or above. Options: critical, high, mediumnocritical
output-filePath to save JSON scan results (relative to workspace root)nonifra-results.json
sarif-filePath to save SARIF output for GitHub Security tab (relative to workspace root)nonifra.sarif
no-aiSkip LLM reasoning — deterministic findings only (no OPENAI_API_KEY required)nofalse
openai-api-keyOpenAI API key for AI-powered exploit reasoning. If not set, uses --no-ai mode.no""
python-versionPython version to use for NIfrano3.12
nifra-versionNIfra version to install (default: latest)no""
upload-sarifUpload SARIF results to GitHub Security tab (requires Advanced Security)notrue
post-pr-commentPost scan results as a PR comment (only on pull_request events)notrue
namedescription
risk-levelOverall risk level: CRITICAL | HIGH | MEDIUM | LOW
findings-countTotal number of findings
critical-countNumber of CRITICAL findings
sarif-pathPath to the generated SARIF file