marketing-plan
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating an attack surface for indirect prompt injection. \n
- Ingestion points: External data enters the context via client materials in
~/marketing-plans/{client-slug}/materials/and outputs from third-party tools like Ahrefs and Stripe. \n - Capability inventory: The skill can write to the local file system and publish to GitHub repositories. \n
- Boundary markers: No explicit delimiters or warnings are used for ingested content. \n
- Sanitization: No explicit sanitization or validation of external content is mentioned. \n- [COMMAND_EXECUTION]: The skill uses various MCP integrations and shell commands. \n
- It performs file read/write operations within
~/marketing-plans/. \n - It executes git commands for repository management and publishing. \n
- It utilizes several MCPs to interact with professional marketing and analytics services. \n- [EXTERNAL_DOWNLOADS]: The skill's documentation recommends installing external CLI tools, specifically
agent-browseranddefuddle, which are used for automated research and extraction tasks.
Audit Metadata