openspec-new
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a user-provided
<change-name>parameter to dynamically generate file system paths and create directories. - Ingestion points: The
<change-name>argument supplied to the/opsx:newcommand (SKILL.md). - Boundary markers: No specific boundary markers or validation rules for the name are defined in the instructions.
- Capability inventory: File system write operations, specifically creating the
openspec/changes/<name>/directory and the.openspec.yamlmetadata file. - Sanitization: There is no mention of sanitizing the user-supplied name, which could potentially allow path traversal (e.g.,
../../../etc/) if the input is not validated by the agent or the platform.
Audit Metadata