academic-peer-reviewer

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists solely of natural language instructions for the agent to adopt a specific persona (Academic Peer Reviewer) and follow a structured evaluation workflow. There is no evidence of malicious patterns, obfuscation, or attempts to bypass safety filters.
  • [NO_CODE]: The skill does not include any scripts, binaries, or command-line operations. It relies entirely on the agent's internal reasoning capabilities to perform the manuscript review.
  • [PROMPT_INJECTION]: While the skill is designed to process untrusted user data (manuscript drafts), which creates a surface for Indirect Prompt Injection, the skill possesses no capabilities (such as network access, file system writes, or shell execution) that could be exploited.
  • Ingestion points: The manuscript text provided by the user in the prompt.
  • Boundary markers: None explicitly defined in the workflow instructions.
  • Capability inventory: No tools, subprocesses, or network operations are defined or requested.
  • Sanitization: None present, but not required given the lack of exploitable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:44 AM
Security Audit — agent-trust-hub — academic-peer-reviewer