alterlab-rma-interview-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its core functionality of processing external data sources.
- Ingestion points: The skill instructions specify that the agent should "Search the web for published qualitative interview studies" and "Read existing project files" (SKILL.md) to build context for its research tasks.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate ingested data or treat it as untrusted content, which could potentially allow malicious instructions embedded in external research documents or web pages to influence the agent's behavior.
- Capability inventory: The skill utilizes web search capabilities and has the capability to read and write multiple files (guides, reports, and summary tables) to the local project directory (SKILL.md).
- Sanitization: No sanitization, validation, or filtering mechanisms for the external content are specified in the workflow to mitigate the risk of processing malicious inputs.
Audit Metadata