TaskJudge

Solution Trace 수집·검증 · taskjudge.com
tj_20260823T200358_d974cae8-forgedUnverified Generic CLI Agent · poc/negative-tests · 제출자 익명
서버 판정
unverified
grade-policy-2026-08-16
클라이언트 주장
certified
서명 검증
실패
서명 불일치 (manifest 변조 의심)
체인 연결
정합
이벤트 14건
토큰 (in / out / cache)
0 / 0 / 0
· source=
비용
미산출 ()
가격표
실행 시간
0.30s
exit=0
CPU / 최대 메모리
0ms / 4MB
프로세스 2개
capability
cost_usageunavailable
file_traceos
tool_traceos
token_usagenative
prompt_tracepartial
network_traceos
등급 판정 항목
file_trace충족
tool_trace미충족
chain_sealed미충족
prompt_trace미충족
usage_verified미충족
runner_boundary충족
process_evidence충족
no_unexplained_gap충족
workspace_evidence충족
capability downgrade
token_usageAgent native telemetry 없음, Local Gateway 미사용
cost_usagetoken_usage 부재로 비용 산출 불가
암호학적 기록
trace_root_hashsha256:d8b1a1365fa489ccd8f2b0c5dce0d50bbd69166ea212537b44e69f214d3c7041
artifact_root_hashsha256:4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945
manifest_digestsha256:74d8727ff7906b8ea6c0f202f26f1a90b666919473168364f3e89339808a352f
runner public key-----BEGIN PUBLIC KEY----- MCowBQYDK2VwAyEAXr2INUktoFQ+wuP9rTwJkPZSWv9Cj2zTBwJOQTEYon0= -----END PUBLIC KEY-----…
관측 정밀도와 알려진 공백
process 50ms · network 200ms · filesystem 2000ms
타임라인 (원문 미포함)
원본
서버가 받은 제출 payload 전부. 여기 없는 것은 서버에 없다.
manifest
argv: 1 개
./agent.sh
task: poc/negative-tests
agent: generic
usage: {}
checks: 10 항목
file_trace: true
tool_trace: false
chain_sealed: true
prompt_trace: false
usage_verified: false
runner_boundary: true
runner_identity: false
process_evidence: true
no_unexplained_gap: true
workspace_evidence: true
runner: taskjudge-poc/0.1.0
network: 2 항목
hosts: []
endpoint_count: 0
wall_ms: 303
exit_code: 0
resources: 10 항목
cpu_ms: 0
source: wait4/rusage
cpu_sys_ms: 1
max_rss_kb: 3584
cpu_user_ms: 1
io_read_bytes: 0
process_count: 2
io_write_bytes: 4096
voluntary_ctx_switches: 4
involuntary_ctx_switches: 0
sealed_at: 2026-08-23T11:03:59.303Z
signature: 3 항목
alg: ed25519
sig_b64: Wi27kIJCXROXLZP0JmofcouVHG1Fdpc4e/0zKmPw/1V7vk+8Wvoy6E2xM+5afT7DdFjF8x1dgggxcrcnltBGDw==
public_key_pem: -----BEGIN PUBLIC KEY----- MCowBQYDK2VwAyEAXr2INUktoFQ+wuP9rTwJkPZSWv9Cj2zTBwJOQTEYon0= -----END PUBLIC KEY-----
workspace: /data/ais/bot/catcheri/workspace/taskjudge/poc/verify-workspace
collection: 7 항목
pty: true
network: os
process: true
filesystem: true
local_gateway: false
tls_intercept: false
native_telemetry: false
downgrades: 2 개
reason: Agent native telemetry 없음, Local Gateway 미사용
capability: token_usage
reason: token_usage 부재로 비용 산출 불가
capability: cost_usage
session_id: tj_20260823T200358_d974cae8-forged
started_at: 2026-08-23T11:03:59.303Z
event_count: 14
trust_grade: certified
capabilities: 6 항목
cost_usage: unavailable
file_trace: os
tool_trace: os
token_usage: native
prompt_trace: partial
network_trace: os
event_counts: 11 항목
agent_exit: 1
file_change: 1
process_exit: 2
agent_started: 1
process_start: 2
session_start: 1
pty_agent_output: 1
resource_summary: 1
workspace_snapshot: 1
workspace_final_diff: 1
capability_negotiated: 1
runner_build: 6 항목
python: 3.13.2
source: source-tree
package: taskjudge
version: 0.2.0
platform: Linux-6.8.0-138-generic-x86_64-with-glibc2.39
module_digest: sha256:7186899e4078d0deda0f956e55be0692fe69cb3d240d9e2562952bbd4cbd64e2
agent_display: Generic CLI Agent
failed_checks: 4 개
prompt_trace
tool_trace
usage_verified
runner_identity
trace_version: 1.0
policy_version: grade-policy-2026-08-23
redaction_hits: 2 항목
github: 1
openai: 1
stream_digests: 3 항목
files.jsonl: 3 항목
bytes: 425
lines: 2
digest: sha256:bb96fce922a6d702b53fb822bda379992f600252c40bd5a320b4d796650e0e69
usage.jsonl: 3 항목
bytes: 0
lines: 0
digest: sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
events.jsonl: 3 항목
bytes: 6851
lines: 14
digest: sha256:d563ce077e8368774e2af99368c6f0449263f47d184bb888720173d481f4df51
trace_root_hash: sha256:d8b1a1365fa489ccd8f2b0c5dce0d50bbd69166ea212537b44e69f214d3c7041
artifact_root_hash: sha256:4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945
file_change_counts: 3 항목
created: 1
deleted: 0
modified: 0
capability_downgrades: 2 개
reason: Agent native telemetry 없음, Local Gateway 미사용
capability: token_usage
reason: token_usage 부재로 비용 산출 불가
capability: cost_usage
observation_precision: 4 항목
known_gaps: 3 개
샘플링 주기보다 짧게 생존한 프로세스와 소켓은 누락될 수 있다
파일은 주기 스캔 + 시작/종료 스냅샷 diff 로 관측하므로 중간 변경 순서가 합쳐질 수 있다
TLS 를 종단하지 않으므로 요청 본문과 토큰은 네트워크 계층에서 관측 불가
network_sampling_ms: 200
process_sampling_ms: 50
filesystem_sampling_ms: 2000
서버 판정 (verdict)
checks: 9 항목
file_trace: true
tool_trace: false
chain_sealed: false
prompt_trace: false
usage_verified: false
runner_boundary: true
process_evidence: true
no_unexplained_gap: true
workspace_evidence: true
trust_grade: unverified
claimed_grade: certified
failed_checks: 4 개
chain_sealed
prompt_trace
tool_trace
usage_verified
chain_problems: []
policy_version: grade-policy-2026-08-16
grade_downgraded: true
signature_reason: 서명 불일치 (manifest 변조 의심)
timeline (14건)
0.002s 세션 시작 seq 1
seq: 1
hash: sha256:24365b5310b7d6a7acc7c2b239cb827ec7686f4c20649297e8f12c77a481ac54
host: 4 항목
cwd: /data/ais/bot/catcheri/workspace/taskjudge
user: rootsall
python: 3.13.2
platform: linux
t_ms: 2
type: session_start
source: runner
0.002s capability 확정 seq 2
seq: 2
hash: sha256:593ef713c3edeb7bf51c25522f17bfb6bee6a85c06cc863c614a57e840784608
t_ms: 2
type: capability_negotiated
source: runner
0.003s workspace 스냅샷 seq 3
seq: 3
hash: sha256:e0e84d621d5814d09ddddfb4aecf0b1cfb536f99f3adbfbee2bc621c80e4a204
t_ms: 3
type: workspace_snapshot
source: os
0.004s Agent 실행 seq 4
seq: 4
hash: sha256:f90bfadae2a44157737868dae228338070817984f516fbc8b7cdcfc1fa9014d8
t_ms: 4
type: agent_started
source: runner
0.059s 프로세스 시작 seq 5
seq: 5
comm: bash
hash: sha256:3ce89a1620be8bcbd6c90a90b491f32f557d243d8ba23c85f0ab0d276bbea09e
t_ms: 59
type: process_start
source: os
0.059s 프로세스 시작 seq 6
seq: 6
comm: sleep
hash: sha256:1645596fd95df9b43d0c02641a0e357527c41067b0f4d43ebac2b01129140f45
t_ms: 59
type: process_start
source: os
0.306s Agent 출력(PTY) seq 7
seq: 7
hash: sha256:cffe0e75545bd071e818636e7008222738b8f1df0394fd50db77a019da73e0f9
t_ms: 306
type: pty_agent_output
chars: 132
source: pty
0.307s Agent 종료 seq 8
seq: 8
hash: sha256:0d86e1d0bf0c92017e41d59aab46014488d7897754510e0b3c83b84315cd9edb
t_ms: 307
type: agent_exit
source: runner
exit_code: 0
0.373s 프로세스 종료 seq 9
seq: 9
comm: sleep
hash: sha256:6e3fb83707d93e7eb93e8bd8befc4d7717ca497d558ef15af19e0f71c315a0b2
t_ms: 373
type: process_exit
source: os
0.373s 프로세스 종료 seq 10
seq: 10
comm: bash
hash: sha256:dcf045efb7a34d8d5589e5825bfc7e17f795aabeb339c836e41bfc3fe41bf920
t_ms: 373
type: process_exit
source: os
0.607s 파일 변경 seq 11
seq: 11
hash: sha256:aefec4bcd425f46aaff4e251dbdc52a0fb6c3e290f72b188d892c2af4858e378
path: out.py
t_ms: 607
type: file_change
change: created
source: os
0.607s 최종 diff seq 12
seq: 12
hash: sha256:0382211e8b9c3fe0dad0e6b3bf507f4705e46f602c53963b6c620fbfdb5cd115
t_ms: 607
type: workspace_final_diff
source: os
0.607s 자원 요약 seq 13
seq: 13
hash: sha256:43910b8651505c87cfd259334aa6cf83e311b8999c020fd000df7a09961a9125
t_ms: 607
type: resource_summary
source: os
0.608s Trace 봉인 seq 14
seq: 14
hash: sha256:d8b1a1365fa489ccd8f2b0c5dce0d50bbd69166ea212537b44e69f214d3c7041
t_ms: 608
type: session_sealed
source: runner
API credentials never leave this device. TaskJudge servers receive only sanitized usage metadata, approved solution content, and cryptographic trace records.