alterlab-nmc-social-analyst
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 ingest and process data from untrusted external sources, which presents a surface for indirect prompt injection vulnerabilities.
- Ingestion points: The agent is instructed to 'Search the web' for platform demographics and algorithm updates and 'Read existing project files' such as content calendars and analytics exports (SKILL.md).
- Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore potential instructions embedded within the external content or project files.
- Capability inventory: The skill has the capability to perform web searches and write deliverables as markdown files to the local project directory.
- Sanitization: There are no defined mechanisms for sanitizing or validating the content retrieved from web searches or project files before it is processed or included in deliverables.
Audit Metadata