howto-code-in-rust

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the use of 'ed3d-research-agents' for internet research and examining external implementations. These are vendor resources provided by the skill author for documentation and pattern lookup.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through its recommendation to process data from untrusted external sources.
  • Ingestion points: Data retrieved from external repositories via 'ed3d-research-agents:remote-code-researcher' as described in 'SKILL.md'.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings for external data.
  • Capability inventory: The agent is instructed to modify, review, and write code based on the findings.
  • Sanitization: Absent; no validation or filtering process for the retrieved content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 06:44 AM
Security Audit — agent-trust-hub — howto-code-in-rust