commerce@0.3.0
VERIFIEDPublisher claims: "Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
Code inventory arrives with this version's next honeypot run.- It will ask for
- unknown until the next run
- Where it talks to
- unknown until the next run
- What the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
The run was clean; the code inventory is pending. Server started and answered tools/list. What the code asks for and which hosts it names arrive with the next run; until then, connect it under the guard with the network pinned to what the honeypot saw.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-07 and scored it 90/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
/** The kill switch: idempotent, final, and never a reversal of anything recorded. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.description: "The kill switch. Stops the run so no further proposal can be recorded under it, with a stated reason. Stopping is idempotent and cannot be undone; start a new run only with fresh operatoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** The kill switch: idempotent, final, and never a reversal of anything recorded. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.description: "The kill switch. Stops the run so no further proposal can be recorded under it, with a stated reason. Stopping is idempotent and cannot be undone; start a new run only with fresh operatoFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.var COMMERCE_AGENT_INSTRUCTIONS = "Decionis CommerceAgent runs under a bounded mandate. Start one run with commercegate_agent_start_run before proposing commerce actions: it fixes the objective, the pFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** The kill switch: idempotent, final, and never a reversal of anything recorded. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.declare const COMMERCE_AGENT_INSTRUCTIONS = "Decionis CommerceAgent runs under a bounded mandate. Start one run with commercegate_agent_start_run before proposing commerce actions: it fixes the objectFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.var COMMERCE_AGENT_INSTRUCTIONS = "Decionis CommerceAgent runs under a bounded mandate. Start one run with commercegate_agent_start_run before proposing commerce actions: it fixes the objective, the pFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for @decionis/commerce@0.3.0 as of 7d ago. This is the package itself, not its dependencies.