linkedin-algorithm
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: A comprehensive review of the skill's instructions, metadata, and reference documentation confirms that the content is strictly focused on marketing optimization and LinkedIn strategy. There are no patterns suggesting prompt injection, data exfiltration, or persistence mechanisms.
- [COMMAND_EXECUTION]: The skill includes a local utility script (
scripts/check-output.py) used by the agent to verify deliverable quality. This script performs basic file reading and string matching to check for required keywords and content length. It does not interact with external networks, access sensitive credentials, or utilize unsafe execution patterns such as eval or subprocess shells.
Audit Metadata