ai-marketing-team
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, creating an attack surface for indirect prompt injection.
- Ingestion points:
inputs/competitor-ads/,inputs/ad-performance.csv, andinputs/reviews/(customer-provided content). - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore instructions embedded within these external inputs.
- Capability inventory: The pipeline involves reading these files and writing output files to the
outputs/directory. - Sanitization: No sanitization or validation of external content is specified before interpolation into agent prompts.
- [COMMAND_EXECUTION]: The instructions mandate populating reference files from a hardcoded absolute local path (
A:\Scale AI Skool\Claude\marketing\The AI Marketing Team Playbook.md). This requires the agent to perform file system read operations on a specific, non-standard local path.
Audit Metadata