agent-rust-expert
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a direct ingestion point for user-supplied tasks which could potentially be used for indirect prompt injection if the input contains malicious instructions.\n
- Ingestion points: The $ARGUMENTS placeholder at the end of SKILL.md is the entry point for untrusted data.\n
- Boundary markers: There are no explicit delimiters (e.g., triple quotes or XML tags) or instructions for the agent to ignore commands within the injected text.\n
- Capability inventory: The agent tasked with Rust development typically possesses capabilities for file system manipulation and shell command execution (via Cargo).\n
- Sanitization: The skill does not define any sanitization or filtering logic for the data interpolated via the $ARGUMENTS placeholder.
Audit Metadata