research

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external primary sources and writes to the local repository, which provides a surface for indirect prompt injection attacks. 1. Ingestion points: The agent is instructed to read external content including official documentation, source code, and APIs (referenced in SKILL.md). 2. Boundary markers: The skill does not explicitly instruct the agent to ignore or delimit instructions found within the researched materials. 3. Capability inventory: The agent has the capability to write Markdown files to the repository (referenced in SKILL.md). 4. Sanitization: There is no mention of sanitizing or validating the content retrieved from external sources before processing it or writing it to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:44 PM
Security Audit — agent-trust-hub — research