accessibility
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Safe Behavior] (SAFE): The skill consists entirely of natural language instructions and does not include any scripts or binaries. It does not perform network operations, access sensitive files, or attempt to persist across sessions.- [Indirect Prompt Injection] (SAFE): The skill is designed to process external code snippets through the $ARGUMENTS variable. Although it lacks explicit boundary markers to isolate untrusted data, the skill has no associated tools or capabilities (such as shell access or file writing) that could be leveraged by an attacker.
- Ingestion points: The $ARGUMENTS variable in SKILL.md.
- Boundary markers: Absent; user-provided content is interpolated directly.
- Capability inventory: None; the skill is limited to generating text-based recommendations.
- Sanitization: Absent.
Audit Metadata