outreach-sequences
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/check-output.pydesigned to validate the formatting of generated deliverables. The script reads a file path from command-line arguments and checks for the presence of specific markdown headers and keywords. It does not perform network operations, use unsafe evaluation functions, or modify the file system. - [DATA_EXPOSURE]: No hardcoded credentials, API keys, or access to sensitive local file paths (e.g., SSH keys, environment files) were detected. The skill uses LeadMagic-specific custom fields (e.g.,
lm_email_status) which are consistent with the skill's authorship and intended use for CRM integration. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user context through diagnostic questions to generate sequence blueprints. While it lacks explicit sanitization for this input, the risk is mitigated by the structured output format and the absence of high-privilege tool capabilities that could be exploited via injection. The implementation uses standard markdown templates to maintain structure.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute scripts from remote servers. All referenced files are local artifacts or documentation paths within the repository structure.
Audit Metadata