pw-embedded-c-style
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a standard attack surface for indirect prompt injection because it ingests user-provided descriptions and code snippets to generate or optimize C code.
- Ingestion points: User prompts requesting project creation or code optimization in
SKILL.md. - Boundary markers: None present; the skill does not instruct the agent to use specific delimiters to isolate user-supplied data from internal instructions.
- Capability inventory: The skill is limited to generating C source code, header files, and project structures based on hardcoded templates.
- Sanitization: No explicit input validation or sanitization of user-provided content is mentioned. As this is the core intended purpose of the skill, the severity is minimal.
- [SAFE]: The code snippets provided for hardware configuration (timers, interrupts, LCD drivers) are standard for embedded development and do not contain any hidden or malicious command execution patterns. The skill does not perform network operations, access sensitive file paths, or install external dependencies.
Audit Metadata