threads-writer-codex
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists solely of natural language instructions and text-based templates. It does not include any scripts, binary files, or shell commands.
- [DATA_EXPOSURE]: The skill specifies reading from a 'context/' directory and writing to an 'outputs/' directory. These are standard local file operations for context ingestion and result storage, with no mechanism for network exfiltration or unauthorized data access.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes content from external files, it lacks access to sensitive capabilities such as network tools, code execution, or administrative commands, ensuring that any instructions embedded in the source data cannot be used to compromise the system.
Audit Metadata