media-plan-builder
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted external data.
- Ingestion points: Data enters the context through the 'BUSINESS INPUTS', 'AUDIENCE INPUTS', and 'COMPETITIVE INPUTS' sections defined in
SKILL.md(Step 1 of the workflow). - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the agent when processing these user-supplied inputs.
- Capability inventory: No subprocess calls, code execution, file writing, or network operations were detected in the skill scripts.
- Sanitization: There is no evidence of input validation, escaping, or sanitization of the provided data before it is used to generate the media plan templates.
- [EXTERNAL_DOWNLOADS]: The skill provides references and links to external resources owned by the author.
- Evidence: Links point to the vendor's official GitHub repository (
github.com/Synter-Media-AI/free-skills) and their primary website (syntermedia.ai) for further tools and automation.
Audit Metadata