paper-comic
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external, untrusted research papers provided via file paths or URLs.
- Ingestion points: The skill accepts local PDF paths and URLs like arxiv.org for analysis as described in the SKILL.md file.
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted paper content from the agent's internal reasoning prompts.
- Capability inventory: The skill uses capabilities to read local files, access the network to download papers, and invoke external image generation tools such as imagegen or baoyu-image-gen.
- Sanitization: The instructions do not specify any methods for sanitizing or filtering the content of the research papers before processing.
- [EXTERNAL_DOWNLOADS]: The skill retrieves research paper data from external sources like arxiv.org to perform its core analysis function.
Audit Metadata