tenzir-cim
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of static documentation and configuration data files.
- No executable scripts (Python, JavaScript, Shell) are included in the skill package.
- The AI instructions in SKILL.md focus on routing questions to appropriate data files and provide standard mapping rules for Splunk data normalization.
- [DATA_EXPOSURE]: No hardcoded credentials or sensitive environment access were found.
- While fields such as 'password' and 'private_key' are defined in the YAML schema (e.g.,
data/fields/password.yaml), they are part of the standard Splunk CIM specification used for field mapping and do not represent actual secrets or exfiltration instructions. - [INDIRECT_PROMPT_INJECTION]: The skill contains a large surface of untrusted data interpolation points (mapping user logs to CIM).
- Ingestion points: User queries containing log samples or questions about field mappings (SKILL.md).
- Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions embedded in user-supplied logs.
- Capability inventory: None. The skill does not use any dangerous tools, subprocess calls, or network operations.
- Sanitization: Not applicable as no code is executed.
- Given the total absence of executable capabilities or network access, the risk of indirect prompt injection is negligible.
Audit Metadata