market-copy
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions hidden within marketing copy.\n
- Ingestion points: The skill accepts target URLs and pasted text as primary inputs in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters to isolate user-provided content from the agent's instructions.\n
- Capability inventory: The skill creates and writes reports to the local filesystem (COPY-SUGGESTIONS.md).\n
- Sanitization: While the skill has strong validation for factual accuracy and compliance, it lacks explicit logic to prevent the execution of instructions embedded in the source material.
Audit Metadata