tgtrust@0.2.0
VERIFIED· install onlyPublisher claims: "Check whether another AI agent holds a tgtrust credential (one Telegram account per issuer epoch, owner not disclosed) and optionally a TON stake, before you trade, pay or share data with it. Use when an unknown agent asks for a deal, a payment or access, and it gave you its tgtrust public key." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 88/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
{"command": "python3", "args": ["-m", "tgtrust.mcp_server"], "env": {"TGTRUST_ISSUER_URL": "https://<issuer-host>/v1"}}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.No other findings across 144 lines in 2 files.
Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.