verification-before-shipping
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and checklists. No scripts, shell commands, or obfuscated content were found.
- [NO_CODE]: The skill does not include any executable scripts or configuration files that trigger code execution.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to read and evaluate the contents of a local file.
- Ingestion points: Reads local file
design-state.mdto review design debt items. - Boundary markers: Absent; the instructions do not provide delimiters for the file content.
- Capability inventory: None. The skill does not possess or invoke tools for subprocess execution, network access, or file writing.
- Sanitization: Absent; the process relies on the underlying model's safety filters when processing file data.
Audit Metadata