paper-introduction-argument-writer
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate tasks related to academic writing and document management. It follows a disciplined approach to structuring arguments without any suspicious commands or exfiltration patterns.
- [PROMPT_INJECTION]: While the skill ingests user-controlled content from LaTeX files and project artifacts (a potential surface for indirect prompt injection), the risk is inherent to the task of document revision and is managed by the agent's standard operating boundaries.
- Ingestion points: Reads local paper drafts (
main.tex,paper.tex, etc.) and project configuration files (paper/.agent/*) inSKILL.md. - Boundary markers: Not explicitly defined for ingested file content.
- Capability inventory: Tool access includes
Write,Edit, andBashas configured in the skill frontmatter. - Sanitization: No explicit sanitization or filtering of ingested text content is specified.
Audit Metadata