discover-research

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions or metadata.
  • [NO_CODE]: The skill contains no executable scripts, shell commands, or network operations. It functions exclusively as a markdown-based configuration and navigation guide.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest external files from the <cc-polymath-root>/skills/research/ directory.
  • Ingestion points: Multiple Read instructions targeting localized markdown files (e.g., research-synthesis.md, quantitative-methods.md).
  • Boundary markers: None present in the loader file.
  • Capability inventory: No subprocess calls, file-write operations, or network operations are present within this skill file.
  • Sanitization: No evidence of sanitization or validation of the content of the target files within this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:23 PM