research-review

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown documentation and YAML frontmatter. There are no scripts, binaries, or configuration files that execute commands or perform network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill's stated purpose is to ingest and critique research papers or drafts provided by the user. While this creates a surface for potential indirect prompt injection from the content of the research artifact, the skill itself provides no evidence of dangerous interpolation or exploitable tool capabilities that would escalate this risk. The file even contains a preventative instruction directing the agent not to search for local prompt templates, which reduces the risk of unintended file system access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:46 AM