Skip to content
skillsafebeta
← Report library
Purpose / Development

Domain Modeling Skill Security Audit

What the author says it does (original text)

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

Independent security check

Security risks found

Files checked
4
Risks found
1
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.No risks found
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.No risks found
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.Risks found: 1
Medium risk

Terminology discussion alone can trigger repository writes without per-change confirmation

Source references: 3
What we found

The Skill applies to ordinary codebase terminology discussions, but also directs the agent to update CONTEXT.md immediately once a term is resolved and to create the file if absent. It does not require showing a patch or obtaining explicit confirmation before each write.

Why this matters

A repository document may be created or changed when the user only intended to discuss or explore the model. Language that the user has not finally approved could then become an authoritative glossary used by developers or later AI agents.

The source supports this risk. The Skill may activate when the user is merely discussing codebase terminology, yet it directs the agent to modify `CONTEXT.md` immediately when a term is resolved and to create the file if absent. It does not require per-write consent. A normal discussion could therefore produce persistent repository changes. Users can ask the author for a read-only discussion mode and require an explicit request plus patch preview before applying changes.

SKILL.md:3In the instructionsOpen original file
name: domain-modelingdescription: Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.---
Show 2 other places
SKILL.md:40In the instructionsOpen original file
Create files lazily: only when you have something to write. If no `CONTEXT.md` exists, create one when the first term is resolved. If no `docs/adr/` exists, create it when the first ADR is needed.
SKILL.md:60In the instructionsOpen original file
### Update CONTEXT.md inlineWhen a term is resolved, update `CONTEXT.md` right there. Don't batch these up: capture them as they happen. Use the format in [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md).
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.No risks found
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.No risks found

Inside this skill

2 instruction sections

This Skill checks existing glossary terms and code while discussing project terminology and domain boundaries, then records clarified domain language. Its stated purpose also includes writing or editing CONTEXT.md and ADRs.

View source
SKILL.md:3In the instructionsOpen original file
name: domain-modelingdescription: Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.---
SKILL.md:46In the instructionsOpen original file
When the user uses a term that conflicts with the existing language in `CONTEXT.md`, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y. Which is it?"
SKILL.md:58In the instructionsOpen original file
When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible. Which is right?"

CONTEXT.md is restricted to a domain glossary without implementation details. In multi-context repositories, the Skill uses CONTEXT-MAP.md to select a target context and asks the user when that target is unclear.

View source
SKILL.md:64In the instructionsOpen original file
`CONTEXT.md` should be totally devoid of implementation details. Do not treat `CONTEXT.md` as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.
CONTEXT-FORMAT.md:56In the instructionsOpen original file
- If `CONTEXT-MAP.md` exists, read it to find contexts- If only a root `CONTEXT.md` exists, single context- If neither exists, create a root `CONTEXT.md` lazily when the first term is resolvedWhen multiple contexts exist, infer which one the current topic relates to. If unclear, ask.

The Skill only offers an ADR when a decision is hard to reverse, surprising without context, and based on a real trade-off; numbering is chosen by scanning existing ADRs and incrementing the highest number.

View source
SKILL.md:68In the instructionsOpen original file
Only offer to create an ADR when all three are true:1. **Hard to reverse**: the cost of changing your mind later is meaningful2. **Surprising without context**: a future reader will wonder "why did they do it this way?"3. **The result of a real trade-off**: there were genuine alternatives and you picked one for specific reasonsIf any of the three is missing, skip the ADR. Use the format in [ADR-FORMAT.md](./ADR-FORMAT.md).
ADR-FORMAT.md:27In the instructionsOpen original file
Scan `docs/adr/` for the highest existing number and increment by one.
Start here · InstructionsSKILL.md
domain-modeling
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source.

File reference map

References: 2
Files making referencesReferenced content
Lines show actual file references, not execution order. Select a node to highlight its connections and inspect the files and source locations. Dashed lines include files that still need locating.
Files and check records4 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included
  • ADR-FORMAT.mdFull text included
  • CONTEXT-FORMAT.mdFull text included
  • agents/openai.yamlFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • ADR-FORMAT.mdSupporting file
  • CONTEXT-FORMAT.mdSupporting file
  • SKILL.mdInstructions
  • agents/openai.yamlSupporting file
Lines read
188
File checksum (to compare versions)
b5b5731ffa238e84789ef3f85f33fffa73dbfba895a8cfdb8e3b21993d3bf6b3