marketing-first-principles
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not include any scripts, executable code, or external dependencies.
- [NO_CODE]: The skill contains no executable scripts or command-line operations, significantly reducing the attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill references local files for strategic context, creating a potential surface for indirect prompt injection if those files contain untrusted instructions. 1. Ingestion points: .agents/marketing-strategy.md and .agents/marketing-learnings.md. 2. Boundary markers: None specified to isolate external content from instructions. 3. Capability inventory: None. The skill lacks tools or instructions to perform network requests, file writes, or command execution. 4. Sanitization: None performed on ingested content.
Audit Metadata