manage-large-files
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no malicious code, remote downloads, or hidden behavior.
- [PROMPT_INJECTION]: The skill addresses potential indirect prompt injection by identifying ingestion points (commit messages, patches, and logs) and establishing boundary markers that instruct the agent to ignore embedded instructions and treat the content as data only.
- [COMMAND_EXECUTION]: The instructions mandate secure command execution practices, such as using '--end-of-options' and avoiding shell interpolation, to mitigate injection risks when processing untrusted file paths or adversarial names.
- [DATA_EXFILTRATION]: No patterns of data exfiltration or hardcoded credentials were detected. The skill explicitly requires the protection of credentials and sensitive objects during LFS operations.
Audit Metadata