ac-context-compactor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): No shell commands or system-level executions are performed. The script only uses standard library modules for data processing.
- [DATA_EXFILTRATION] (SAFE): The skill does not perform any network requests or external data transfers. All file operations are confined to the local project directory.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download external scripts or packages. It relies entirely on Python's standard library.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes project files (feature_list.json), it only extracts metadata for summary generation. It does not possess high-risk capabilities (like network access or command execution) that could be leveraged by malicious content in those files.
Audit Metadata