quality-editor
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely within the local project context, reading and writing to predefined markdown files for manuscript editing and reporting. It does not use external tools or network-based resources.
- [PROMPT_INJECTION]: The skill processes manuscript drafts and analysis files which represent an indirect prompt injection surface. This vulnerability surface allows external content to potentially influence the agent's behavior during the review process.
- Ingestion points: Reads untrusted text from 'manuscript_draft.md', 'literature_matrix.md', and files within the 'paper_analyses/' directory.
- Boundary markers: The skill does not employ specific delimiters or 'ignore' instructions to isolate the manuscript content from the agent's core instructions.
- Capability inventory: The skill has file-write permissions for 'manuscript_draft.md', 'review_report.md', and 'IMPLEMENTATION_PLAN.md'.
- Sanitization: There is no evidence of sanitization or validation of the ingested paper content before it is processed.
Audit Metadata