ai-visibility-panel-design
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves a data ingestion surface where external prompt architectures and candidate ledgers are processed to design measurement panels.
- Ingestion points: The skill reads
prompt_architecture.jsonand candidate rejection ledgers as specified in the 'Inputs' section ofSKILL.md. - Boundary markers: No specific delimiters or boundary warnings are defined for the imported JSON or candidate data.
- Capability inventory: The skill is restricted to generating structured documentation (
tracking_plan.md,panel.yaml,run_manifest_template.json); it does not contain subprocess calls, network operations, or dynamic code evaluation. - Sanitization: The skill relies on 'QA-approved' status and human-decision artifacts as logic-based filters rather than programmatic sanitization or escaping of input data.
Audit Metadata