skills/joseph-lozano/skills/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external primary sources such as official documentation, source code, and APIs. This introduces a vulnerability surface where an attacker-controlled external source could contain hidden instructions that the agent might inadvertently follow during the research process.
  • Ingestion points: Investigating external primary sources including official docs, source code, specs, and first-party APIs as specified in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions found within the researched content.
  • Capability inventory: The agent has the capability to write to the local file system (saving results as Markdown files in the repo).
  • Sanitization: There is no evidence of sanitization, filtering, or validation logic to process the external data before it is incorporated into the research findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:27 AM
Security Audit — agent-trust-hub — research