analyze-paper

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection from the contents of the academic papers it processes. \n
  • Ingestion points: Technical data and text are ingested from the user-provided <paper-path> in SKILL.md. \n
  • Boundary markers: No explicit delimiters or instructions to ignore commands within the paper are provided to the agent. \n
  • Capability inventory: The agent reads the paper and sibling reference files (e.g., in ~/.claude/skills/reaper/), and writes the resulting summary back to the workspace. \n
  • Sanitization: The instructions do not specify any validation or sanitization of the input text before extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 10:26 AM
Security Audit — agent-trust-hub — analyze-paper