alterlab-rma-abstract-writer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest research documents and web search results, which creates a potential surface for indirect prompt injection.
- Ingestion points: The SKILL.md instructions direct the agent to read project files (paper drafts, notes) and search the web for requirements.
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate ingested content from core instructions.
- Capability inventory: The skill uses search, read, and write tool capabilities within its defined workflow.
- Sanitization: No specific validation or sanitization logic is provided for external data processing.
- [COMMAND_EXECUTION]: The skill describes using tools for searching the web and managing files, which are standard for an academic writing tool and align with its stated purpose.
Audit Metadata