ohos-req-arch-decision
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behaviors or security vulnerabilities were detected. The skill's operations are limited to reading local project documentation and writing formatted Markdown results.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted external data from requirement and feasibility documents. However, the risk is minimal as the skill lacks high-privilege capabilities such as shell execution or network access.
- Ingestion points: Reads content from
{docs_dir}/01-requirement.mdand{docs_dir}/02-feasibility.mdto build the decision record. - Boundary markers: The skill uses structural instructions but lacks explicit delimiters or warnings to ignore instructions embedded within the source documents.
- Capability inventory: File system access is restricted to reading and writing Markdown files in the project directory. No subprocess execution or network tools are utilized.
- Sanitization: No explicit sanitization or filtering of input data is mentioned, but output is constrained by a strict ADR template.
Audit Metadata