Skip to content

    Type a page, a command such as keryn scan, or a rule id.

    prompt-redaction-ordering-v2

    View as Markdown

    6 rules · Keryn Software Licence · rules 0.8.0 · all packs

    How to read a rule
    Severity
    How bad the finding is if it is real: error fails a default gate, warning and info do not.
    Confidence
    P0 exploitable as written; P1 dangerous in context; P2 a heuristic or a posture check: confirm by reading the code.
    False-positive risk
    low: an exact API or flag, so hits are almost always real; medium: the pattern is legitimate in many programs, so check each hit; high: it finds a lead to confirm, so expect benign hits.
    Edge
    The relationship the finding sits on. reaches: content or traffic gets to a thing; calls: one thing invokes another; reads: one thing reads from another; writes: one thing writes to another; sends: data leaves for another party; grants: authority is given or left unchecked; depends_on: something relies on a component it does not verify; trusts: one party believes another without evidence. The boundary it crosses, when there is one: user->prompt (untrusted input reaching a prompt); model->code (model output reaching code, a shell, a query or a page); secret->outside (a secret leaving the trusted side); supply-chain (code, models or prompts pulled in from outside).
    Taxonomy chips
    References for readers who work in OWASP LLM 2025, OWASP Agentic, CWE or NIST AI RMF. They say where a rule belongs, not that a framework is satisfied.

    seceng.redaction.prompt-logged-before-redaction-ts

    Section titled “seceng.redaction.prompt-logged-before-redaction-ts”

    warning typescript, javascript prompt-redaction-ordering

    Prompt/messages/completion data is logged before visible redaction, masking, classification, or hashing.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: sends data leaves for another party.

    CWE-532 CWE-200 LLM02 LLM07 GOVERN MANAGE

    seceng.redaction.prompt-logged-before-redaction-python

    Section titled “seceng.redaction.prompt-logged-before-redaction-python”

    warning python prompt-redaction-ordering

    Prompt/messages/completion data is logged before visible redaction, masking, classification, or hashing.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: sends data leaves for another party.

    CWE-532 CWE-200 LLM02 LLM07 GOVERN MANAGE

    seceng.redaction.trace-attributes-raw-ai-context

    Section titled “seceng.redaction.trace-attributes-raw-ai-context”

    info typescript, javascript, python, java, csharp prompt-redaction-ordering

    Tracing span attributes include raw prompt, messages, completion, tool args, or system prompt without visible redaction.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: reads one thing reads from another.

    CWE-532 LLM02 LLM07 ASI01 ASI02 GOVERN MANAGE

    warning typescript, javascript, python, java, csharp, go, rust prompt-redaction-ordering

    Full LLM request or response body is logged. Prefer structured redaction and prompt hashes over raw payload logging.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: sends data leaves for another party.

    CWE-532 LLM02 LLM07 GOVERN MANAGE

    warning typescript, javascript, python, java, csharp prompt-redaction-ordering

    Tool/function call arguments are logged before visible filtering. Tool args may contain secrets, PII, URLs, file paths, or tenant data.

    Confidence P2: a heuristic or a posture check: confirm by reading the code. False-positive risk medium: the pattern is legitimate in many programs, so check each hit.

    Edge inspected: calls one thing invokes another.

    CWE-532 LLM02 LLM06 LLM07 ASI03 ASI02 GOVERN MANAGE

    seceng.redaction-langsmith-langfuse-capture-raw-prompts

    Section titled “seceng.redaction-langsmith-langfuse-capture-raw-prompts”

    info typescript, javascript, python prompt-redaction-ordering

    LangSmith/Langfuse/Helicone or telemetry configuration appears to capture raw prompts/messages/completions without redaction controls.

    Confidence P1: dangerous in context. False-positive risk high: it finds a lead to confirm, so expect benign hits.

    Edge inspected: sends data leaves for another party.

    CWE-532 LLM02 LLM07 GOVERN MANAGE