proofread
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from lecture files (e.g., .tex and .qmd), which represents an ingestion surface for indirect prompt injection attacks where malicious instructions hidden in the files could influence the agent's behavior.
- Ingestion points: Files identified via the Glob tool in Slides/ and Quarto/ directories or provided as arguments (SKILL.md).
- Boundary markers: No delimiters or isolation instructions are defined to separate the data (lecture content) from the agent's proofreading instructions.
- Capability inventory: The skill has access to Read, Grep, Glob, Task, and Write tools. The Write tool is utilized to save analysis reports to the quality_reports/ directory (SKILL.md).
- Sanitization: No content filtering or validation of the input files is performed prior to processing by the proofreader agent.
Audit Metadata