literature-review

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (academic papers via paper-search and paper CLI tools) and processes it using tools with write and shell access (Bash, Write). This creates a surface where malicious instructions embedded in paper text or metadata could attempt to override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:29 AM
Security Audit — agent-trust-hub — literature-review