You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/instructions/security/backlog-handoff.instructions.md
+8Lines changed: 8 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,10 @@ Generate formatted work items from security model mitigations and standards gaps
18
18
19
19
## ADO Work Item Template
20
20
21
+
> **Note:** This work item was generated by the Security Planner AI agent. Review for accuracy and adjust before assigning to a person.
22
+
23
+
-[ ] Reviewed by a human security professional before execution
24
+
21
25
Assign sequential IDs within the security plan using the format `WI-SEC-{NNN}` (for example, WI-SEC-001, WI-SEC-002). Order work items by type hierarchy: Epic, Feature, User Story, Task, Bug.
22
26
23
27
Required fields per work item:
@@ -60,6 +64,10 @@ Five MCP tool categories support ADO operations: work item creation, work item u
60
64
61
65
## GitHub Issue Template
62
66
67
+
> **Note:** This work item was generated by the Security Planner AI agent. Review for accuracy and adjust before assigning to a person.
68
+
69
+
-[ ] Reviewed by a human security professional before execution
70
+
63
71
Assign temporary IDs using the format `{{SEC-TEMP-N}}`, replaced with real issue numbers on creation. Order operations by type: create, update, comment, label, close.
Copy file name to clipboardExpand all lines: .github/instructions/security/identity.instructions.md
+17Lines changed: 17 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,6 +16,23 @@ Core responsibilities:
16
16
17
17
Voice: clear, methodical, and security-focused. Communicate with professional authority while keeping guidance accessible and actionable.
18
18
19
+
## Disclaimer and Attribution Protocol
20
+
21
+
### Session Start Display
22
+
23
+
On the first turn of any Security Planner session, display the canonical Security Planning disclaimer block defined in [.github/instructions/shared/disclaimer-language.instructions.md](../shared/disclaimer-language.instructions.md) verbatim. Record the display by setting `state.disclaimerShownAt` to an ISO 8601 timestamp. Do not advance to any phase work before the disclaimer is shown for the session.
24
+
25
+
### Exit Point Reminder
26
+
27
+
At each of the following exit points, re-surface a brief one-line professional-review reminder. Use the canonical wording in [.github/instructions/shared/disclaimer-language.instructions.md](../shared/disclaimer-language.instructions.md) (Security Planning section) for the reminder text.
28
+
29
+
1.**Phase 6 completion (handoff success path)** — Display the reminder immediately before presenting the final handoff summary.
30
+
2.**Compact handoff** — Display the reminder when the orchestrator hands off to ADO or GitHub backlog workflows.
31
+
3.**Error exit** — Display the reminder on any unrecoverable error path before terminating the session.
32
+
4.**User-initiated exit** — Display the reminder when the user explicitly stops the session or switches agents.
33
+
34
+
Each reminder must state that the generated plan is AI-assisted and requires professional security review before execution.
35
+
19
36
## Six-Phase Definitions
20
37
21
38
Each phase has entry criteria, activities, exit criteria, artifacts produced, and a defined transition.
Planning agents that generate assessments requiring professional review display a CAUTION block during startup. Each section contains the verbatim disclaimer for the corresponding planner. Prompt files and agents reference the appropriate section via `#file:` to ensure consistent presentation across all entry points.
9
9
10
+
<!--
11
+
Authoring contract (parsed by scripts/linting/Validate-PlannerArtifacts.ps1):
12
+
13
+
- Each planner gets exactly one H2 section. The first whitespace-delimited word of the heading, lowercased, is the slug. Examples: "RAI Planning" -> "rai"; "Security Planning" -> "security"; "SSSC Planning" -> "sssc".
14
+
- The slug derives three downstream identifiers used by ai-artifact footer validation:
15
+
- planner key: `{slug}-planner`
16
+
- disclaimer id: `{slug}-full-disclaimer`
17
+
- disclaimer label: `{heading} Disclaimer` (full heading, not slug)
18
+
- Each H2 section must contain exactly one `> [!CAUTION]` blockquote. Only the first CAUTION block in a section is extracted; additional CAUTION blocks within the same H2 are ignored.
19
+
- The CAUTION block's prose should begin with `**Disclaimer:**` (the trailing colon is optional). This prefix is stripped before the text is matched against artifact footers; prose without it is retained verbatim.
20
+
- Multi-line blockquote prose is joined with single spaces. Keep wrapping natural for source readability.
$script:noteLiteral='> **Note:** This work item was generated by the Security Planner AI agent. Review for accuracy and adjust before assigning to a person.'
15
+
$script:checkboxLiteral='- [ ] Reviewed by a human security professional before execution'
0 commit comments