construct-perspective-set
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML-formatted metadata. It does not include any executable scripts, binaries, or configuration files that could perform actions on the underlying system.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data through its input contract parameters (e.g., 'target_object'). While this data is interpolated into the agent's context, the skill lacks any dangerous capabilities that could be exploited through injection.
- Ingestion points: Input contract parameters (target_object, perspective_basis, selection_goal) defined in SKILL.md.
- Boundary markers: The skill does not implement specific boundary markers or instructions to ignore embedded commands in the processed inputs.
- Capability inventory: No tools, network operations, file system writes, or command execution capabilities are defined or requested in the frontmatter or body.
- Sanitization: No input sanitization or validation logic is present.
Audit Metadata