aeon-paper-pick
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted content from external paper abstracts and titles.
- Ingestion points: The skill fetches metadata from the Hugging Face Papers endpoint (huggingface.co/papers) as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from following instructions that might be embedded within the paper text.
- Capability inventory: The agent is tasked with reading, scoring, and summarizing external content, which is a common behavior for research agents.
- Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the agent.
Audit Metadata