matlab-review-fi-object-code
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to ingest and evaluate external MATLAB code which may contain malicious instructions intended to influence agent behavior.
- Ingestion points: MATLAB source files containing fixed-point logic as defined in the checklist in
SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters to separate the reviewed code from the agent's instructions.
- Capability inventory: Uses
evaluate_matlab_codeandcheck_matlab_code(permanifest.yaml) which can execute or analyze the untrusted input files. - Sanitization: Absent. No mention of filtering or validating input code for malicious natural language content before processing.
Audit Metadata