Skip to content
Report library
Purpose / Writing

Writing Fragments Skill Security Audit

What the author says it does (original text)

Writing, explore: mine raw fragments, no structure yet.

Independent security check

Security risks found

Files checked
2
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

Conversation content is silently persisted before item-by-item approval

Source references: 5
What we found

The Skill captures the initial prompt and fragments produced by either participant while instructing the agent not to request permission for each fragment. Fragments may include private material such as complaints or confessions. Choosing a path does not necessarily approve every later passage for persistence.

Why this matters

Sensitive, unfinished, or unwanted material—and model-generated wording the user has not endorsed—may enter a lasting document. Because the format does not identify whether the user or model supplied a fragment, its origin and approval status may later be unclear.

Saving fragments to a user-chosen Markdown file is the Skill’s stated purpose, so file writing is not hidden. However, once invoked it captures material from both sides starting with the initial prompt and explicitly appends each fragment without per-item permission. If the conversation contains confessions, quotations, or other material the user did not intend to retain, it may still be persisted. A user can ask for sensitive-content exclusions, a preview or explicit-confirmation mode, and restrict the destination to a dedicated file.

SKILL.md:11In the instructionsOpen original file
As fragments emerge from either side of the conversation, append them to a single markdown file.If the user did not pass a path, ask once where to save the document, then remember it for the rest of the session.Capture fragments from the very first thing the user says, including the initial prompt.
Show 4 other places
SKILL.md:35In the instructionsOpen original file
- A list of related observations that hang together by feel.- A complaint, a confession, a punchline.- A **leading word**: a compact metaphor or coinage the whole piece can hang on (one term that names the idea, the way _tracer bullets_ or _fog of war_ names a whole pattern).
SKILL.md:69In the instructionsOpen original file
Fragments are separated by a horizontal rule (`\n---\n`). No headings inside the body. No tags. No order beyond the order they were added.
SKILL.md:73In the instructionsOpen original file
Append silently. Don't ask permission for each fragment. Mention what you added in passing ("adding that"), but don't interrupt the conversation with save dialogs.Before every write: re-read the file from disk. The user may have edited, reordered, or deleted fragments between turns, so preserve their changes. Never overwrite the file; only append (or, if the user asks, edit a specific fragment in place).
SKILL.md:13In the instructionsOpen original file
If the user did not pass a path, ask once where to save the document, then remember it for the rest of the session.Capture fragments from the very first thing the user says, including the initial prompt.
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

3 instruction sections

The Skill conducts an open-ended writing interview and continuously appends resulting fragments to one Markdown file; outlining and article structure are explicitly excluded.

View source
SKILL.md:9In the instructionsOpen original file
This is pure **explore**: widen the space of what could be written without committing to structure. Committing is _exploit_, a separate skill's job. Run a grilling session that produces fragments, interviewing the user relentlessly about whatever they want to write about. Imposing phases, outlines, or article structure is out of scope here.As fragments emerge from either side of the conversation, append them to a single markdown file.

If no save path is supplied, the Skill asks once. A newly created document starts with only a working title, and later fragments are separated by horizontal rules.

View source
SKILL.md:13In the instructionsOpen original file
If the user did not pass a path, ask once where to save the document, then remember it for the rest of the session.Capture fragments from the very first thing the user says, including the initial prompt.On first write, put a single H1 at the top with a working title (it can change later) and nothing else: no metadata, no TOC, no date.
SKILL.md:69In the instructionsOpen original file
Fragments are separated by a horizontal rule (`\n---\n`). No headings inside the body. No tags. No order beyond the order they were added.

Before each write, the Skill requires rereading the file and preserving the user's on-disk changes. It normally appends only and edits an existing fragment in place only when requested.

View source
SKILL.md:75In the instructionsOpen original file
Before every write: re-read the file from disk. The user may have edited, reordered, or deleted fragments between turns, so preserve their changes. Never overwrite the file; only append (or, if the user asks, edit a specific fragment in place).The user can say "cut the last one", "rewrite that one sharper", "merge those two" at any time. Treat those as first-class instructions.

The configuration disables implicit invocation, so its file-writing workflow should begin only after the user explicitly selects the Skill.

View source
SKILL.md:2In the instructionsOpen original file
---name: writing-fragmentsdescription: "Writing, explore: mine raw fragments, no structure yet."disable-model-invocation: true---
agents/openai.yaml:4In the instructionsOpen original file
  short_description: "Mine raw writing fragments"policy:  allow_implicit_invocation: false
Start here · InstructionsSKILL.md
writing-fragments
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

Operations mentioned in code and instructions

Read files
SKILL.md:75In the instructionsOpen original file
Before every write: re-read the file from disk. The user may have edited, reordered, or deleted fragments between turns, so preserve their changes. Never overwrite the file; only append (or, if the user asks, edit a specific fragment in place).
Lines read
86
File checksum (to compare versions)
3028f161622908c9302949bd68dd4a2ad28e7497b36dd6e2f94e988dec0ea0f3