slack-search
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill exhibits no malicious behavior and follows standard implementation patterns for a local search utility.
- [DATA_EXFILTRATION]: All data access is confined to local JSON index files within the skill's directory structure. There are no network operations or credentials involved.
- [COMMAND_EXECUTION]: The Python implementation uses safe file reading and string matching techniques. It does not use subprocesses or any form of dynamic code evaluation.
- [PROMPT_INJECTION]: The skill does not attempt to override AI safety instructions or agent behavior. It returns structured search results, which limits the potential for indirect prompt injection from the indexed content.
Audit Metadata