slide-excellence
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from slide files (.qmd and .tex) provided by the user. While these files are untrusted data that could contain embedded instructions, the skill's capabilities are limited to reading, searching, and writing quality reports within a localized environment.
- Ingestion points: File content parsed from $ARGUMENTS and accessed via 'Read' and 'Grep' tools.
- Boundary markers: None present.
- Capability inventory: 'Read', 'Grep', 'Glob', 'Write', 'Task'.
- Sanitization: None explicitly defined for processing file contents.
Audit Metadata