batch-content-plan
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains no instructions designed to override system safety protocols, bypass constraints, or extract system prompts. The instructional tone is strictly focused on content planning logic.
- [DATA_EXFILTRATION]: No sensitive file paths (such as .ssh, .aws, or .env) are accessed. The skill reads local brand and voice configuration files which is consistent with its stated purpose. No unauthorized network operations were detected.
- [REMOTE_CODE_EXECUTION]: There is no evidence of remote script execution, such as curl-to-bash patterns, or the use of dynamic execution functions like eval() or exec().
- [CREDENTIALS_UNSAFE]: The skill does not contain any hardcoded API keys, tokens, or other sensitive credentials. It follows best practices by assuming credentials and connections are handled by the platform (WoopSocial).
- [COMMAND_EXECUTION]: No shell commands or subprocess calls were found. The skill operates through natural language instructions and bridging to other internal skills.
- [SAFE]: The skill logic is transparent and focuses on organizational tasks. It includes quality checks and confirmation steps before handing tasks to scheduling services, which promotes user oversight.
Audit Metadata