alterlab-nmc-web-strategist
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 process untrusted data from multiple sources, which could lead to indirect prompt injection if the source data contains malicious instructions.
- Ingestion points: The skill instructions in SKILL.md require the agent to search the web for SEO practices and competitor structures, and to read project-specific files such as analytics reports, content inventories, and brand guidelines.
- Boundary markers: There are no instructions to wrap external data in delimiters or use specific markers to distinguish between the skill's instructions and the ingested data.
- Capability inventory: The agent is authorized to write multiple markdown files (site maps, SEO briefs, audit reports) to the local project directory.
- Sanitization: The skill lacks instructions for validating, escaping, or filtering content retrieved from external web searches or provided project files before processing them.
Audit Metadata