bad-antics/Prompt Armor — AI Injection Scanner

Scan prompt files and templates for AI injection attacks. 8-layer detection, 17 attack vectors.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
pathsGlob pattern for files to scan (default: prompts/, templates/, *.txt, *.md)no.
thresholdMinimum threat level to fail: suspicious, hostile, or critical (default: hostile)nohostile
output-formatOutput format: text or jsonnotext
max-filesMaximum number of files to scanno100
namedescription
total-scannedTotal files scanned
threats-foundNumber of threats above threshold
highest-threatHighest threat level found
reportJSON scan report