ad-creative
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external landing page URLs and local brand configuration files to generate ad copy. This allows potential malicious content from a website to influence the agent's output or quality scoring.
- Ingestion points: External landing page URLs and local brand files in ~/.claude-marketing/.
- Boundary markers: No specific delimiters or safety instructions are defined to separate the untrusted external data from the skill's core instructions.
- Capability inventory: The skill uses specialized agents to generate text, evaluate compliance, and suggest testing strategies based on the ingested content.
- Sanitization: There is no evidence of sanitization or validation logic to filter potentially malicious instructions from the external URLs or local data files.
Audit Metadata