paper7-research

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches academic papers from arXiv, which is a well-known and trusted academic repository. This is a functional requirement of the skill.
  • [COMMAND_EXECUTION]: The skill utilizes the paper7 command-line tool to search for and retrieve paper content. It also performs standard file system operations and git commits to save research briefs.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to the nature of processing external paper content.
  • Ingestion points: External data from arXiv is retrieved via the paper7 get command and stored in temporary files (e.g., /tmp/kb_paper1.md) before being read by the agent.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings when processing the content of the retrieved papers.
  • Capability inventory: The agent is empowered to execute shell commands, write to the filesystem, and perform git commits based on its synthesis of the untrusted data.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the fetched paper content before the agent extracts findings and recommendations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 01:31 AM
Security Audit — agent-trust-hub — paper7-research