vibe-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from competitors and analytics reports to inform marketing strategy and content generation.
- Ingestion points: Prompts in
SKILL.md(Phase 1 and Phase 5) instruct the agent to research competitors and process analytics data. - Boundary markers: There are no explicit delimiters or instructions to the model to ignore potential commands embedded in the external content.
- Capability inventory: The skill includes a validation script (
scripts/check-output.py) and generates content for various marketing platforms. It lacks direct file-write or network-exfiltration capabilities that could be abused via injection. - Sanitization: The skill does not provide mechanisms to sanitize or validate the external data before it is used in prompt interpolation.
Audit Metadata