Skip to content

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

    remote-prompt-template-supply-chain-v2

    View as Markdown

    7 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.promptsc.langchain-hub-prompt-unpinned

    Section titled “seceng.promptsc.langchain-hub-prompt-unpinned”

    warning python, typescript, javascript langchain

    LangChain Hub prompt is pulled without a pinned commit, owner allowlist, or review gate.

    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: depends_on something relies on a component it does not verify; it crosses the supply-chain boundary (code, models or prompts pulled in from outside).

    CWE-829 CWE-20 LLM01 LLM03 LLM07 ASI03 ASI04 ASI01 MAP GOVERN MANAGE

    info python, typescript, javascript remote-prompt-template-supply-chain

    Prompt template or agent instruction is loaded from a remote URL at runtime without visible pinning, signature, or allowlist.

    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: depends_on something relies on a component it does not verify; it crosses the supply-chain boundary (code, models or prompts pulled in from outside).

    CWE-829 CWE-20 LLM01 LLM03 LLM07 ASI01 ASI04 ASI02 MAP GOVERN MANAGE

    seceng.promptsc.yaml-agent-config-remote-tools

    Section titled “seceng.promptsc.yaml-agent-config-remote-tools”

    info generic mcp, browser-extension

    Agent YAML/JSON config references remote prompt, remote tool manifest, or remote MCP server without visible trust controls.

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

    Edge inspected: depends_on something relies on a component it does not verify; it crosses the supply-chain boundary (code, models or prompts pulled in from outside).

    CWE-829 LLM01 LLM03 LLM06 LLM07 ASI04 ASI02 ASI01 MAP GOVERN

    seceng.promptsc.prompt-template-from-database-without-version

    Section titled “seceng.promptsc.prompt-template-from-database-without-version”

    info python, typescript, javascript, php, java, csharp remote-prompt-template-supply-chain

    Prompt/system/developer template is loaded from database or CMS without visible version, approval, or integrity metadata.

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

    Edge inspected: trusts one party believes another without evidence.

    CWE-345 LLM01 LLM07 ASI02 ASI01 GOVERN MANAGE

    seceng.promptsc.env-controlled-system-prompt

    Section titled “seceng.promptsc.env-controlled-system-prompt”

    info python, typescript, javascript remote-prompt-template-supply-chain

    System/developer prompt is controlled by environment variable. Verify deployment controls, auditability, and prompt integrity.

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

    Edge inspected: reaches content or traffic gets to a thing; it crosses the user->prompt boundary (untrusted input reaching a prompt).

    CWE-15 LLM01 LLM07 ASI01 GOVERN MANAGE

    info python, typescript, javascript mcp, browser-extension

    MCP manifest, tool definition, or remote server config is loaded from URL without visible allowlist/signature validation.

    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-829 LLM03 LLM06 LLM07 ASI01 ASI02 ASI04 MAP GOVERN MANAGE

    info typescript, javascript, python, php, java, csharp github-actions

    Runtime route or admin endpoint edits prompt/template/tool instructions without visible authorization and approval workflow.

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

    Edge inspected: grants authority is given or left unchecked.

    CWE-862 LLM01 LLM06 LLM07 ASI03 ASI02 ASI01 GOVERN MANAGE