- Add Prompt Defense Baseline to agent-evaluator (was the only agent missing it)
- Update AGENTS.md to document all 67 agents (36 were previously unlisted)
- Add routing guidance for 11 additional agents in orchestration section
- Count in header kept at 67 (matches actual agents/ folder count)
Audit findings (documented but not changed):
- 3 agents (doc-updater, opensource-forker, opensource-packager) use model:haiku
with Write/Edit tools; intentional for lightweight pipeline tasks
- 6 agents have non-standard color: field (loop-operator, harness-optimizer,
gan-*, performance-optimizer); may be harness-specific UI metadata
- 7 agents are <=60 lines; thin but sufficient for narrow scope
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Git commands (log, diff, show) can execute arbitrary code via:
- core.pager set in repo-local .git/config
- diff.external pointing to an attacker-controlled binary
- filter drivers in .gitattributes
Mitigation: require --no-pager flag, recommend -c core.pager=cat
to disable pager-driven execution. Moved git commands from the
unqualified allowlist to a hardened allowlist with explicit flags.
- Replace httpx.Retry references with correct httpx API usage across all files
(httpx has no built-in Retry class; use HTTPTransport/Limits instead)
- Fix _check_summary to check first 100 words (not 100 characters)
- Fix template to only show → improvement arrow for non-5 scores
- Clarify hook documentation: hook echoes reminder, does not run evaluator
- Add return type annotation to main()
- Make required parameter keyword-only in _read_file_or_text
- evaluate.py: add CRITICAL ISSUES (axes ≤ 2) section, VERDICT line
- agent-evaluator.md: match format_report output exactly (title, evidence markers, bar graphs)
- templates/evaluation-report.md: match evaluate.py output format
- All now produce identical AGENT SELF-EVALUATION REPORT structure
Single authoritative format: evaluate.py's format_report() output.
