mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-05-14 02:10:07 +08:00
docs: record AgentShield HTML report evidence
Records AgentShield PR #59 in the ECC 2.0 GA roadmap and moves the next AgentShield roadmap slice to the remaining prompt-injection benchmark/PDF decision work. Validation: - npx --yes markdownlint-cli docs/ECC-2.0-GA-ROADMAP.md - npm test (2324 tests) - npm run harness:audit -- --format json (70/70) - npm run harness:adapters -- --check (PASS, 11 adapters) - npm run observability:ready (14/14) - GitHub Actions matrix green on PR #1796
This commit is contained in:
parent
a96787736d
commit
a8c03ad350
@ -52,6 +52,9 @@ As of 2026-05-12:
|
||||
- AgentShield PR #58 added MCP package provenance fields and report-level
|
||||
counts for npm vs git, pinned vs unpinned, known-good, and registry-backed
|
||||
supply-chain evidence.
|
||||
- AgentShield PR #59 added self-contained HTML executive summaries with risk
|
||||
posture, critical/high priority findings, category exposure, README/API
|
||||
docs, built-CLI smoke validation, and 1,704-test coverage.
|
||||
- ECC PR #1778 recovered the useful stale #1413 network/homelab architect-agent
|
||||
concepts.
|
||||
- ECC-Tools PR #26 added cost/token-risk predictive follow-ups for AI routing,
|
||||
@ -178,7 +181,8 @@ Acceptance:
|
||||
path for npm/pip reputation, CVEs, typosquats, and dependency risk.
|
||||
- Prompt-injection corpus and regression benchmark are ready for continuous
|
||||
rule hardening.
|
||||
- Enterprise reports include JSON plus HTML/PDF or equivalent executive output.
|
||||
- Enterprise reports include JSON plus self-contained HTML executive output
|
||||
with risk posture, priority findings, and category exposure.
|
||||
|
||||
### 6. ECC Tools Billing, Deep Analysis, PR Checks, And Linear Sync
|
||||
|
||||
@ -222,7 +226,7 @@ Acceptance:
|
||||
|
||||
## Next Engineering Slices
|
||||
|
||||
1. Extend AgentShield enterprise reporting beyond terminal/JSON supply-chain
|
||||
evidence toward executive HTML/PDF or equivalent report output.
|
||||
1. Finish AgentShield prompt-injection corpus/regression benchmark work and
|
||||
decide whether PDF export adds value beyond the merged HTML executive report.
|
||||
2. Extend ECC Tools deep analysis and Linear/project sync without flooding the
|
||||
workspace.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user