career-exit-management
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [DATA_EXPOSURE]: The skill guides users to create handover documents containing project statuses, key contacts, and system access lists. While it includes explicit warnings to 'pay attention to compliance' and 'not take company property,' it encourages the processing of potentially sensitive organizational data within the agent session.
- [INDIRECT_PROMPT_INJECTION]: The skill uses a template-based approach to generate resignation letters and handover documents. It interpolates user-provided data such as 'Internal reason for leaving' or 'Project descriptions' into these templates.
- Ingestion points: User-supplied text for resignation reasons and project details (SKILL.md).
- Boundary markers: Placeholders like '[姓名]' and '[日期]' are used for interpolation, but there are no explicit instructions for the LLM to ignore embedded instructions in that data.
- Capability inventory: The skill appears to be informational/text-generative only, with no tool-based capabilities (like file system writes or network calls) defined in the frontmatter.
- Sanitization: No explicit sanitization or escaping of user input is mentioned.
- [NO_CODE]: This skill consists entirely of markdown instructions and templates. It does not include any executable scripts, shell commands, or external dependencies, which significantly limits the technical attack surface.
Audit Metadata