cyber-risk-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed exclusively of Markdown documentation and structural templates. It does not include any scripts (.py, .js, .sh), binary executables, or dynamic context injection commands (
!command). - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted external data (e.g., security program documentation, audit results, and incident reports provided by the user). While this establishes an ingestion surface for potentially malicious instructions embedded in those documents, the skill possesses no capabilities (such as file writing, shell execution, or network requests) to exploit. As the skill lacks dangerous tools, this surface represents a negligible risk.
- Ingestion points: Inputs defined in
SKILL.md(Existing security program documentation, audit results). - Boundary markers: Not present in instructions.
- Capability inventory: No tools or executable capabilities identified across the skill.
- Sanitization: Not specified in instructions.
- [DATA_EXFILTRATION]: The skill requests sensitive organizational information (e.g., technology stack, budget context, and past incidents) as inputs for the assessment. However, there are no mechanisms within the skill to exfiltrate this data; no network tools (curl, wget) or hardcoded external domains are present.
Audit Metadata