embedded-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is authored as a professional technical guideline for reviewing C and C++ firmware. It focuses on critical embedded systems concepts like memory safety, ISR correctness, and RTOS primitives without exhibiting any malicious patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (source code provided by a user), which technically presents a surface for indirect prompt injection if that code contains adversarial instructions targeting the LLM. However, the risk is negligible as the skill possesses no exploitable capabilities.
- Ingestion points: Source code files or snippets provided by the user for review in
SKILL.md. - Boundary markers: Absent; the skill relies on the agent's general ability to distinguish between its instructions and the data being analyzed.
- Capability inventory: The skill does not request or use any external tools, shell execution, file system modifications, or network operations.
- Sanitization: No sanitization or filtering is applied to the input code.
Audit Metadata