Skip to content
skillsafebeta
← Report library
Purpose / Documents

Handoff Skill Security Audit

What the author says it does (original text)

Compact the current conversation into a handoff document for another agent to pick up.

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.Risks found: 1
Medium risk

Conversation summary is persisted outside the workspace in an OS temporary directory

Source references: 3
What we found

The Skill explicitly writes the current conversation to a file in the operating system's temporary directory. Although it requires redaction of API keys, passwords, and personally identifiable information, the conversation may contain confidential business details, internal paths, or artifact URLs that are not covered by those examples or are not recognized correctly. The supplied source does not specify the file's exact location, access permissions, or cleanup time.

Why this matters

After invocation, project context may remain somewhere the user would not normally review or clean with the project. If another local process or user can read the temporary file, or if it is retained, information in the summary could be exposed.

The Skill requires explicit invocation, but once invoked it writes a summary of the current conversation to the OS temporary directory rather than the workspace. The summary may also reference artifact paths or URLs. Although API keys, passwords, and personally identifiable information must be redacted, the source does not specify the exact file location, permissions, retention period, or protection for other business-confidential material. This creates a plausible risk that another local user or later process could read the residual summary. A user can ask the author to document permissions and automatic cleanup, or restrict included content and require a controlled destination.

SKILL.md:8In the instructionsOpen original file
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
Show 2 other places
SKILL.md:12In the instructionsOpen original file
Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
agents/openai.yaml:4In the instructionsOpen original file
  short_description: "Compact a conversation into a handoff"policy:  allow_implicit_invocation: false
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
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

0 instruction sections

The Skill permits only explicit invocation. When invoked, it compacts the current conversation into a document for another agent.

View source
SKILL.md:2In the instructionsOpen original file
---name: handoffdescription: Compact the current conversation into a handoff document for another agent to pick up.argument-hint: "What will the next session be used for?"disable-model-invocation: true---
agents/openai.yaml:4In the instructionsOpen original file
  short_description: "Compact a conversation into a handoff"policy:  allow_implicit_invocation: false

The document is written to the operating system's temporary directory rather than the current workspace. It should reference existing artifacts and redact API keys, passwords, and personally identifiable information.

View source
SKILL.md:8In the instructionsOpen original file
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.Include a "suggested skills" section in the document, naming which skills the next agent should call the Skill tool for.Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
Start here · InstructionsSKILL.md
handoff

The instructions have no section headings. Supporting files and code excerpts are available below.

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
23
File checksum (to compare versions)
cba0fa8e7b7c56cf9470828d5506b5feca0c087e9a6167141b0aeb9659b217c3