Skip to content
skillsafebeta
← Report library
Purpose / Other

Loop Me Skill Security Audit

What the author says it does (original text)

Grill me about specs for the workflows I want to build, within this workspace.

Independent security check

Security risks found

Files checked
2
Risks found
2
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.Risks found: 1
Medium risk

Personal and workplace routines are persistently recorded in workspace notes

Source references: 2
What we found

The Skill solicits details about the user's career, weekly and morning activities, tools, and communication channels, and directs that this information be recorded in `NOTES.md`. The source does not direct transmission, but persistent local storage can still expose sensitive patterns.

Why this matters

If the workspace is committed, synchronized, or shared, the notes may reveal schedules, internal tools, communication channels, and business-processing practices.

The source instructs the Skill to interview the user when notes are thin and record their tools, processing channels, and terminology in `NOTES.md`; its definition of a loop explicitly includes career, weekly, and morning activities. If the user discloses such details, personal and work patterns will persist in the workspace and may be readable by people or tools with workspace access. The source does not show network transmission. Users can withhold sensitive details and ask the author to define retention, access scope, and optional fields.

SKILL.md:12In the instructionsOpen original file
A **loop** is a recurring pattern in the user's life: their career, their week, their morning, a single repeated activity. Picturing a life as loops within loops reveals how predictable its activities really are, which is what makes them worth **delegating**. Use the lens to find loops worth specifying, and propose ones the user hasn't noticed.
Show 1 other places
SKILL.md:32In the instructionsOpen original file
- `workflows/*.md`: one spec per workflow.- `NOTES.md`: raw notes on the user's world, the tools they use, the channels they process, and their own terminology for both. When it is empty or thin, interview them about their world before specifying anything. Sharpen fuzzy terms into canonical ones as they surface, and record them here.
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

The interview may delete existing workflow specifications without requiring confirmation

Source references: 3
What we found

The instructions expressly permit creating, editing, and deleting specifications as the interview progresses, but do not restrict deletion to files created during the current session or require a diff, backup, or separate approval.

Why this matters

If `workflows/*.md` already contains useful material, the model could treat an older specification as superseded and remove design history or implementation requirements.

This is an active instruction allowing specs to be created, edited, and deleted as the interview progresses, while those files are defined as the source of truth. It does not limit deletion to files created in the current session or require confirmation or backup. When the Skill is used, existing `workflows/*.md` files could therefore be removed while resolving questions, losing specifications or changing the basis for later implementation. A user can ask the author to define deletion scope and require a preview and explicit confirmation before deletion.

SKILL.md:8In the instructionsOpen original file
Run a stateful `/grilling` session whose only output is **workflow** specs. Use the grilling discipline (relentless, a round of questions at a time, a recommended answer attached to each) aimed at the vocabulary and goal below. Create, edit, and delete specs as the grilling resolves things.
Show 2 other places
SKILL.md:31In the instructionsOpen original file
- `workflows/*.md`: one spec per workflow.- `NOTES.md`: raw notes on the user's world, the tools they use, the channels they process, and their own terminology for both. When it is empty or thin, interview them about their world before specifying anything. Sharpen fuzzy terms into canonical ones as they surface, and record them here.
SKILL.md:14In the instructionsOpen original file
A **workflow** is the spec of one loop, made real. You run a workflow on a loop: the loop is its running instantiation. Workflows live in `workflows/*.md` and are the source of truth.
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

4 instruction sections

This Skill is an explicitly invoked workflow-interview tool. It uses persistent rounds of questions and writes the result as `workflows/*.md` specifications, which it may create, edit, or delete.

View source
SKILL.md:8In the instructionsOpen original file
Run a stateful `/grilling` session whose only output is **workflow** specs. Use the grilling discipline (relentless, a round of questions at a time, a recommended answer attached to each) aimed at the vocabulary and goal below. Create, edit, and delete specs as the grilling resolves things.
SKILL.md:14In the instructionsOpen original file
A **workflow** is the spec of one loop, made real. You run a workflow on a loop: the loop is its running instantiation. Workflows live in `workflows/*.md` and are the source of truth.
agents/openai.yaml:4In the instructionsOpen original file
  short_description: "Spec the workflows you want to build"policy:  allow_implicit_invocation: false

The Skill interviews the user about work, daily life, tools, and communication channels, then persistently records that information in `NOTES.md`. The supplied source contains no network upload, script execution, or installation step.

View source
SKILL.md:12In the instructionsOpen original file
A **loop** is a recurring pattern in the user's life: their career, their week, their morning, a single repeated activity. Picturing a life as loops within loops reveals how predictable its activities really are, which is what makes them worth **delegating**. Use the lens to find loops worth specifying, and propose ones the user hasn't noticed.
SKILL.md:32In the instructionsOpen original file
- `workflows/*.md`: one spec per workflow.- `NOTES.md`: raw notes on the user's world, the tools they use, the channels they process, and their own terminology for both. When it is empty or thin, interview them about their world before specifying anything. Sharpen fuzzy terms into canonical ones as they surface, and record them here.
Start here · InstructionsSKILL.md
loop-me
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source.
Files and check records2 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
  • 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.

  • SKILL.mdInstructions
  • agents/openai.yamlSupporting file
Lines read
39
File checksum (to compare versions)
506dfd0e518de6774faabb2de43f89104fb63a1555c01f56d95a3d72c0f86b68