rust-skill-creator
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to use shell utilities such as
mkdir,ls, andcatto create and manage a directory structure for generated skills at~/.claude/skills/. It also involves writing newSKILL.mdand reference files based on templates. - [EXTERNAL_DOWNLOADS]: Content is fetched from well-known and trusted Rust community domains, specifically
docs.rsanddoc.rust-lang.org. These sources are standard for the intended technical documentation purpose. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes untrusted documentation content which is then used to generate instructions for the agent's future behavior.
- Ingestion points: Documentation content is fetched from external URLs via
agent-browserorWebFetchas described in SKILL.md. - Boundary markers: Absent; the fetched content is interpolated directly into skill templates without delimiters or "ignore" instructions.
- Capability inventory: The skill has the capability to write files and create directories on the local filesystem (
~/.claude/skills/). - Sanitization: No sanitization, escaping, or validation of the retrieved documentation content is performed before it is written into new instructions.
Audit Metadata