skills/gdewitte/agentic/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external primary sources such as official documentation, source code, and APIs. This introduces a surface for indirect prompt injection, where malicious instructions embedded in those external sources could attempt to influence the agent's behavior during the research process.
  • Ingestion points: Processes external primary sources like documentation and APIs (SKILL.md).
  • Boundary markers: No explicit delimiters are specified to separate external content from internal instructions.
  • Capability inventory: The skill has file system write access to save markdown files within the repository (SKILL.md).
  • Sanitization: No specific sanitization or filtering of external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:30 PM
Security Audit — agent-trust-hub — research