alterlab-rma-academic-writer
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 untrusted external data from project files such as drafts, research notes, and supervisor feedback.
- Ingestion points: The 'Workflow' and 'Agentic Protocol' sections describe the agent reading existing project files for context.
- Boundary markers: The skill does not explicitly specify the use of delimiters or instructions to ignore embedded commands within the user-provided files.
- Capability inventory: The agent possesses capabilities to perform web searches and write files to the local directory.
- Sanitization: No specific filtering or sanitization protocols for the ingested file content are mentioned. Note: This risk is inherent to the skill's primary function of reviewing academic documents.
- [SAFE]: No evidence of malicious behavior, data exfiltration, or unauthorized command execution was found. The skill's stated purpose of providing academic writing assistance aligns with its defined capabilities and workflow.
Audit Metadata