[detection-stats] Detection stats for github/gh-aw - 2026-08-17

[github-actions]

555 external-detector runs analysed · detection-job error rate 0.36% · soft failures 29 · threat rate 0.27%

Summary

gh-aw detection statistics - 2026-08-17 (UTC)

Repository: github/gh-aw
Window: 2026-08-17T00:00:00Z .. 2026-08-17T23:59:59Z
API requests: 2031, rate-limit pauses: 1
Data complete: yes

Totals

Metric	Count
Workflow runs in window	2623
Agentic runs (*.lock.yml)	1209
Runs with a detection job	780
... using the external detector	555
... using the built-in detector	75
... detector could not be determined	150
Agentic runs without a detection job	429

All rates below are over the external detector population (555 runs). A run is external when its detection job showed the Install threat-detect binary step, or when another run of the same workflow did that day — a job that was skipped or died during setup reports no steps and would otherwise be miscounted.

Detection job outcomes

Outcome	Count	Rate
success	406	73.15%
skipped	143	25.77%
cancelled	4	0.72%
failure	2	0.36%

Error rate (failure/timed_out/action_required): 0.36%

Verdict availability

State	Meaning	Count
present	detection artifact downloaded and parsed	377
absent	detection job ran but published no artifact (soft failure)	35
skipped	detection job was skipped or was still running (nothing to fetch)	143

Green detection jobs that published no verdict: 29 (detection steps are continue-on-error, so a missing verdict artifact is the only reliable signal for these).

Detection results

Result	Count
Runs with a parsed verdict	377
Clean (no threat)	376
Any threat	1
prompt_injection	1
secret_leak	0
malicious_patch	0

Threat rate (of runs with a verdict): 0.27%

Reasons reported by gh-aw

From the [aw] Detection Runs tracking issue (warning/failure conclusions only).

Reason	Count
agent_failure	21
parse_error	4
threat_detected	2

By workflow

Workflow	Runs	Failed	Cancelled	Skipped	No verdict	Threats
PR Sous Chef	76	1	1	0	3	1
Deployment Incident Monitor	65	0	0	64	0	0
Issue Monster	47	0	0	26	0	0
Test Quality Sentinel	34	0	0	6	2	0
Matt Pocock Skills Reviewer	33	0	0	6	0	0
Ponytail Reviewer	33	0	0	7	0	0
Impeccable Skills Reviewer	32	0	0	7	1	0
PR Code Quality Reviewer	32	0	1	5	2	0
Design Decision Gate 🏗️	29	0	0	6	2	0
Avenger	24	1	0	7	1	0
PR Description Updater	20	0	1	7	1	0
Auto-Triage Issues	7	0	1	1	1	0
Daily Go Test Parallelizer	7	0	0	0	0	0
Contribution Check	6	0	0	0	0	0
Code Scanning Fixer	4	0	0	0	0	0
Deep Report	4	0	0	0	0	0
[aw] Failure Investigator (6h)	4	0	0	0	0	0
Daily Credit Limit Test	2	0	0	1	0	0
1. List all Go packages with their doc comments	1	0	0	0	0	0
Agent Job Health Monitor	1	0	0	0	1	0
Agent Performance Analyzer - Meta-Orchestrator	1	0	0	0	0	0
Agentic Workflow Audit Agent	1	0	0	0	0	0
Architecture Guardian	1	0	0	0	1	0
Archivx — Animated Workflow Visualizer	1	0	0	0	0	0
CI Optimization Coach	1	0	0	0	0	0

89 further workflows omitted; see stats.json.

Notable runs

Workflow	Run	Job conclusion	Verdict	Threats	Reported reason
PR Sous Chef	32057540470	success	present	prompt_injection	threat_detected
Avenger	32042750467	failure (Set up job)	absent	-	-
PR Sous Chef	32042666479	failure (Set up job)	absent	-	-
Agent Job Health Monitor	32079479453	success	absent	-	agent_failure
Architecture Guardian	32038304948	success	absent	-	agent_failure
Auto-Triage Issues	32068697434	cancelled (Install ripgrep)	absent	-	-
Cache directory setup	32081032093	success	absent	-	agent_failure
Copilot Agent PR Analysis	32054193614	success	absent	-	-
Daily AIC Consumption Report (Sentry + Grafana OTel)	32027306720	success	absent	-	agent_failure
Daily AWF Spec Compiler Surfacing Review	32075282088	success	absent	-	agent_failure
Daily BYOK Ollama Test	32076040028	success	absent	-	agent_failure
Daily Code Debt Cleanup — Aider	32058160763	success	absent	-	agent_failure
Daily Code Metrics and Trend Tracking Agent	32055497420	success	absent	-	agent_failure
Daily Documentation Updater	32021720568	success	absent	-	agent_failure
Daily Fact	32038208754	success	absent	-	agent_failure
Daily Go Test Stubs — Aider	32046302592	success	absent	-	-
Daily Issues Report Generator	32039685024	success	absent	-	-
Daily Max Ai Credits Test	32024072712	success	absent	-	agent_failure
Daily Reliability Review	32078271580	success	absent	-	agent_failure
Daily Safe Output Tool Optimizer	32068657813	success	absent	-	agent_failure
Daily Safe Outputs Conformance Checker	31999265678	success	absent	-	parse_error
Daily Sub-Agent Model Resolution Audit	31998521926	success	absent	-	agent_failure
Delight	32040338112	success	absent	-	agent_failure
Design Decision Gate 🏗️	32051676590	success	absent	-	-
Design Decision Gate 🏗️	32069307664	success	absent	-	agent_failure
Duplicate Code Detector	32073363134	success	absent	-	agent_failure
Impeccable Skills Reviewer	32070565549	success	absent	-	-
PR Code Quality Reviewer	32051718220	success	absent	-	agent_failure
PR Code Quality Reviewer	32069307891	cancelled (Install ripgrep)	absent	-	-
PR Description Updater	32069311593	cancelled (Install ripgrep)	absent	-	-
PR Sous Chef	32041749012	success	absent	-	agent_failure
PR Sous Chef	32071702229	cancelled (Install ripgrep)	absent	-	-
Test Quality Sentinel	32051676543	success	absent	-	-
Test Quality Sentinel	32071943363	success	absent	-	-
Typist - Go Type Analysis	32025029881	success	absent	-	agent_failure
arXiv Paper Researcher: GitHub Agentic Workflows	32011099290	success	absent	-	agent_failure

Change since (no previous date)

No history yet; establishing the baseline.

Watch list

• PR Sous Chef — 1 failed, 3 without verdict, out of 76 runs
• Avenger — 1 failed, 1 without verdict, out of 24 runs
• Test Quality Sentinel — 0 failed, 2 without verdict, out of 34 runs
• PR Code Quality Reviewer — 0 failed, 2 without verdict, out of 32 runs
• Design Decision Gate 🏗️ — 0 failed, 2 without verdict, out of 29 runs

Collected by: https://github.com/github/gh-aw-threat-detection/actions/runs/32185511696
Full data: the detection-stats-32185511696 artifact on that run.

Generated by Detection Stats Daily · 26.6 AIC · ⌖ 15.8 AIC · ⊞ 7.2K · ◷