linkedin-post-writer
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused exclusively on text generation and content strategy for LinkedIn. It does not perform any network operations, file system modifications, or command execution.
- [PROMPT_INJECTION]: The skill includes defensive instructions in the 'Edge cases & pushback' section and 'avoiding-cringe.md' reference. It specifically directs the agent to decline requests for deceptive content, fake stories, or low-quality engagement bait, reinforcing the agent's adherence to its primary purpose and quality standards.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or access to sensitive environment variables or system files were found.
- [EXTERNAL_DOWNLOADS]: The skill does not contain any instructions to download or execute external scripts or packages.
Audit Metadata