ciso-advisor
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected across the skill's instructions, references, or scripts.- [COMMAND_EXECUTION]: The skill includes Python scripts (
risk_quantifier.py,compliance_tracker.py) designed for local risk analysis and compliance mapping. These scripts are safe, utilizing only standard Python libraries and performing no dangerous operations such as network requests or shell command execution.- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest data fromcompany-context.md. While this is an ingestion point for potentially untrusted data, the skill's capabilities are limited to advisory reporting and role invocation, and no malicious overrides were identified. - Ingestion points:
company-context.md(referenced in SKILL.md) - Boundary markers: None present in the provided instructions.
- Capability inventory: Internal role invocation (
[INVOKE:role|question]) and report generation. - Sanitization: Not specified.
Audit Metadata