Skip to content

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

    repo-automation-agent-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.repoagent.model-output-to-git-command

    Section titled “seceng.repoagent.model-output-to-git-command”

    warning typescript, javascript, python repo-automation-agent

    AI/model output is passed into git command or repository operation without visible validation or approval.

    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; it crosses the model->code boundary (model output reaching code, a shell, a query or a page).

    CWE-78 CWE-20 LLM06 LLM09 ASI05 ASI01 ASI02

    warning typescript, javascript, python repo-automation-agent

    PR/issue comment body is passed directly to an agent or tool executor without visible validation. Comments are attacker-controlled prompt-injection sources.

    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-20 LLM01 LLM06 ASI01 ASI02

    seceng.repoagent-write-token-with-autonomous-agent

    Section titled “seceng.repoagent-write-token-with-autonomous-agent”

    info typescript, javascript, python repo-automation-agent

    Repository automation agent appears to have write token permissions without visible approval or policy gate.

    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-266 LLM06 ASI03 ASI02

    seceng.repoagent-generated-code-executed-in-worktree

    Section titled “seceng.repoagent-generated-code-executed-in-worktree”

    warning typescript, javascript, python repo-automation-agent

    AI-generated code or patch appears to be executed in the repository worktree without sandboxing.

    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; it crosses the model->code boundary (model output reaching code, a shell, a query or a page).

    CWE-94 CWE-78 LLM03 LLM06 ASI05 ASI02 ASI10

    warning python repo-automation-agent

    Repository automation agent appears to send secret-bearing files or environment files to an LLM.

    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-200 CWE-798 LLM02 ASI03 ASI02

    warning javascript, typescript repo-automation-agent

    Repository automation agent appears to send secret-bearing files or environment files to an LLM.

    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-200 CWE-798 LLM02 ASI03 ASI02