influencer-marketing-paid
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and marketing templates. No scripts, shell commands, or external dependencies are present.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a conversational workflow that processes untrusted user input via discovery questions.\n
- Ingestion points: User responses to marketing discovery questions (SKILL.md).\n
- Boundary markers: Absent; instructions do not specify delimiters for user-provided data.\n
- Capability inventory: None; the skill does not use any tools, file operations, or network requests.\n
- Sanitization: Absent; the skill relies on the underlying LLM's default safety guardrails.
Audit Metadata