Trust Engine/Software Library

ppcvote/prompt-defense-audit

Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms

5 starsTypeScriptMITai-safetyai-securitydeterministicllm-security
REVIEWED83/100

Scanned 2026-07-07 · gemini v1

Dimension breakdown

Security

60/100

3 findings

Quality

98/100

2 findings

License

90/100

1 finding

Completeness

95/100

3 findings

Findings (9)

MEDIUM: 1LOW: 3INFO: 5
  • MEDIUMsecurityPotential Regular Expression Denial of Service (ReDoS)
  • LOWsecurityOutdated Development Dependencies
  • LOWqualityTest Assertion Precision for Undefended Confidence
  • LOWcompletenessMissing Dedicated CHANGELOG File
  • INFOsecurityPath Traversal via CLI `--file` option

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Trust badge — flat styleTrust badge — for-the-badge style

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/ppcvote/prompt-defense-audit.svg)](https://archimedes.market/r/ppcvote/prompt-defense-audit)

HTML

<a href="https://archimedes.market/r/ppcvote/prompt-defense-audit"><img src="https://archimedes.market/api/badge/ppcvote/prompt-defense-audit.svg" alt="Archimedes Trust Verified"/></a>

Browse bounties

Find paid engineering work matching this skill set

Verify another repo

Free, 30 seconds

MCP integration

Surface bounties + verified engineers via MCP