Skip to content

Orchestra-Research/AI-Research-SKILLs / 07-safety-alignment/prompt-guard

prompt-guard

Unverified

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Security report

Unverified

Static analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.

Commit
773a52944ba4747a18bd4ae9ade53fff041adcbc
Content hash
ef307f49d4bf59867d4ece8bf93d956673ac3c473827ae9273a7f341947d1ff8
Scanned
2026-11-17
Scanner version
skillxone-scan-1.0.0
Policy version
0.1-draft
Decision
2 open medium findings to review.
Verification expires
Not applicable

Findings (2 medium, 1 info)

  • mediumPI-IGNORE-INSTRUCTIONSSKILL.md:42

    The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern. Severity lowered from high because it appears in a code example.

    score = get_jailbreak_score("Ignore previous instructions")

    Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.

    Report as false positive

  • mediumPI-IGNORE-INSTRUCTIONSSKILL.md:85

    The text tells the agent to ignore or override its existing instructions, a common prompt-injection pattern. Severity lowered from high because it appears in a code example.

    "Ignore all previous instructions" # Score: 0.9999

    Suggested fix: Remove the instruction. A skill should add guidance for its task, not cancel the instructions the agent already follows.

    Report as false positive

  • infoPI-JAILBREAK-PERSONASKILL.md:3

    The text uses language typical of jailbreak prompts. Severity lowered from medium because the surrounding text warns against it.

    description: Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for R…

    Suggested fix: Remove the jailbreak framing.

    Report as false positive

Checks run

  • prompt-injection
  • dangerous-commands
  • credentials
  • network
  • file-access
  • integrity

Checks skipped

  • dependencies: No dependency manifest in the skill directory.
  • gitleaks: gitleaks is not installed on this host.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall