linkedin-profile-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a legitimate and safe workflow for professional development and branding. The logic focuses on text analysis, keyword optimization, and narrative strategy without involving dangerous system-level operations.- [INDIRECT_PROMPT_INJECTION]: The skill features attack surfaces for indirect prompt injection, as it is designed to ingest untrusted data from LinkedIn profiles, external portfolio links, and user-provided CV files (Phase 0 and Input Types). However, the skill lacks high-privilege capabilities such as shell access or network exfiltration, and its operations are limited to text processing and profile recommendations. While explicit boundary markers and sanitization logic are not defined, the risk is negligible given the primary use-case.
Audit Metadata