systems-programming-rust-project
Fail
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input via the
$ARGUMENTSvariable to generate directory structures, source code, and configuration files. This creates an attack surface where maliciously crafted requirements could influence the generated output. - Ingestion points: Project requirements are accepted via the
$ARGUMENTSplaceholder within the## Requirementssection ofSKILL.md. - Boundary markers: The skill does not implement delimiters or specific instructions to isolate user-provided requirements from the system's generation logic.
- Capability inventory: The skill generates source code, Makefiles, and build configurations, and it provides instructions for executing shell commands like
cargo new,cargo build, andcargo run. - Sanitization: There is no evidence of input validation, filtering, or escaping for the requirements provided by the user.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata