k2f-cover-letter
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include a command to install a secondary skill ('suzheng/k2f') which serves as the core layout engine. This is a vendor-owned resource provided by the same author for modular functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to process external data like job postings and resumes, which are potentially untrusted sources.
- Ingestion points: The workflow ingests job descriptions, resumes, and candidate notes from the user's environment.
- Boundary markers: There are no specific instructions for the agent to use delimiters or ignore embedded commands when parsing these external inputs.
- Capability inventory: The skill (via its 'k2f' dependency) has the capability to write and export files (PDF, DOCX).
- Sanitization: The instructions do not include steps for sanitizing or filtering input data to prevent malicious instruction overrides.
Audit Metadata