career-profile-builder
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files and reference templates. It does not contain any executable scripts, binaries, or automated routines that could perform unauthorized operations on the host system.
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection because it is designed to ingest and process untrusted data from user-provided resumes or existing career profile files to automate the data entry process.
- Ingestion points: The agent parses external documents in the 'Pass 0 — Triage' and 'When the user already has a profile' sections of SKILL.md.
- Boundary markers: There are no explicit instructions to the agent to distinguish between its core instructions and potentially malicious instructions embedded in the documents being parsed.
- Capability inventory: The skill's operations are limited to text parsing and file I/O for specific career documents; it lacks network access or the ability to execute system commands.
- Sanitization: The instructions do not define methods for sanitizing or validating the content extracted from external documents.
Audit Metadata