alterlab-nmc-digital-campaign
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read local project files and search the web, which creates a surface for indirect prompt injection. \n
- Ingestion points: Local project files (e.g., issue briefs, stakeholder maps) and web search results are ingested into the agent's context during the strategic planning and narrative development phases. \n
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the processed data. \n
- Capability inventory: The agent has the ability to search the web, read files, and write multiple markdown deliverables to the local project directory (e.g., campaign strategies, messaging matrices, and digital toolkits). \n
- Sanitization: No explicit sanitization or validation mechanisms for the ingested content are mentioned in the agent's protocol.
Audit Metadata