ai-assistant: docs/skills: Add skills STRIDE threat model#888
Open
illume wants to merge 1 commit into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a STRIDE threat model document intended to capture security risks and mitigations for an AI “skills” subsystem, focusing on threats like prompt injection, path traversal, and untrusted remote content.
Changes:
- Adds a new threat model document covering STRIDE categories for the skills system.
- Includes a system overview (components, data flow, trust boundaries) and a prioritized mitigation plan.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+1
to
+3
| # STRIDE Threat Model: Headlamp AI Skills System | ||
|
|
||
| ## 1. System Overview |
illume
force-pushed
the
docs/ai-assistant-skills-threat-model
branch
2 times, most recently
from
2c9a7a6 to
053df35
Compare
Comment on lines
+5
to
+9
| The skills system loads Markdown documents ("skills") and injects them into the AI assistant's system prompt. Skills come from: | ||
|
|
||
| 1. **Local directories** — files on disk (configured paths or well-known project directories) | ||
| 2. **Auto-discovered project directories** — `.github/skills/`, `.github/instructions/`, `.claude/skills/`, `skills/` scanned automatically when a project is opened | ||
| 3. **Remote Git repositories** — GitHub zip archives downloaded over HTTPS |
STRIDE threat model for the skills subsystem. Covers threats that arise from loading, parsing, and injecting untrusted skill content into the LLM system prompt: - Spoofing / tampering: malicious skill files served from a compromised HTTP source; mitigated by configurable source allowlists and content-length limits. - Path traversal: zip-slip during zip extraction; mitigated by path canonicalisation in `SkillZipExtractor` before writing any file. - Information disclosure: skill content leaking cluster credentials embedded in YAML; mitigated by treating skill content as user-visible text, not secrets. - Denial of service: oversized skill files exhausting memory; mitigated by `MAX_ZIP_EXTRACTED_BYTES` and `MAX_ZIP_FILE_COUNT` hard limits. - Prompt injection: malicious skill content hijacking LLM behaviour; mitigated by size budgets and content filtering in `SkillRouter` before injection. Signed-off-by: René Dudfield <renedudfield@microsoft.com> Co-authored-by: Ashu Ghildiyal <aghildiyal@microsoft.com> Signed-off-by: Ashu Ghildiyal <aghildiyal@microsoft.com>
illume
force-pushed
the
docs/ai-assistant-skills-threat-model
branch
from
053df35 to
8b32509
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
docs/skills/skills-stride-threat-model.md— a STRIDE threat model for the skills subsystem, covering skill loading, path traversal, and prompt-injection risks with mitigations.Assisted by Copilot.
Part of the ai-assistant skills documentation series.