linkedin-posts
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional content and reference tables for LinkedIn post creation. It does not include any scripts, commands, or automation logic.
- [EXTERNAL_DOWNLOADS]: The skill contains several URLs pointing to official LinkedIn Help and Engineering blog pages. These are well-known, trusted sources for the stated purpose of the skill.
- [PROMPT_INJECTION]: No patterns of instruction override, role-play bypass, or safety filter circumvention were detected in the instructions or metadata.
- [DATA_EXFILTRATION]: There is no evidence of sensitive data access or exfiltration. The skill does not attempt to read system files, environment variables, or credentials.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided content for LinkedIn posts, it lacks any functional capabilities (such as shell access, file writing, or network requests) that could be exploited via malicious data injection.
Audit Metadata