academic-writing-cs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown-based guidelines and templates. It does not contain any scripts, source code, or executable components.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided academic drafts for revision (SKILL.md). While this creates an ingestion point for untrusted data, the skill possesses no capabilities for network exfiltration, file system modification, or command execution, rendering the surface safe. Evidence chain:
- Ingestion points: User-supplied paper drafts (SKILL.md Stages 2 and 3).
- Boundary markers: None explicitly defined in the instructions, though standard Markdown headers are used.
- Capability inventory: No tools for file system writing, network requests, or subprocess execution are present.
- Sanitization: No input sanitization is performed.
Audit Metadata