schema-markup
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, unauthorized filesystem access, or credential exposure patterns were found in the instructions or example files. The skill functions solely as a knowledge base and instruction set for the agent.
- [PROMPT_INJECTION]: The skill instructs the agent to ingest content from .claude/product-marketing-context.md (Ingestion points) to provide task context. No boundary markers are defined to separate this content from system instructions. The skill's capability inventory is restricted to formatting JSON-LD strings and lacks network, shell, or file-write permissions. No sanitization or validation of the ingested content is specified.
Audit Metadata