llm06-agent-tool-approval
4 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:
errorfails a default gate,warningandinfodo 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.llm06.dangerous-tool-without-obvious-approval
Section titled “seceng.llm06.dangerous-tool-without-obvious-approval”info javascript, typescript, python llm06-agent-tool-approval
Tool definition exposes a side-effecting capability. Confirm human approval, RBAC, tenant scoping, and audit logging.
Confidence P1: dangerous in context.
Edge inspected: grants authority is given or left unchecked.
CWE-285 CWE-862 LLM06 ASI03 ASI02
seceng.llm06.email-send-capability
Section titled “seceng.llm06.email-send-capability”warning javascript, typescript, python llm06-agent-tool-approval
Email sending capability found. If callable by an agent, require approval, recipient allowlist, and audit logging.
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-285 LLM06 LLM01 ASI02 ASI01
seceng.llm06.browser-agent-action
Section titled “seceng.llm06.browser-agent-action”warning javascript, typescript, python llm06-agent-tool-approval
Browser action capability found. If model-controlled, require approval, domain allowlist, action allowlist, and dry-run mode.
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-285 LLM06 LLM01 ASI02 ASI01
seceng.llm06.github-write-capability
Section titled “seceng.llm06.github-write-capability”warning javascript, typescript, python llm06-agent-tool-approval
GitHub write capability found. If callable by an agent, require approval, repo allowlist, and audit logging.
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.