recharts
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is instructed to glob and read external project source files to identify Recharts usage and suggest fixes. Instructions embedded within the source code being reviewed could potentially influence the agent's behavior during the correction process.
- Ingestion points: The workflow involves reading
package.jsonand project source files (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the rules.
- Capability inventory: The skill has file system read access and the ability to apply code corrections (file write) (SKILL.md).
- Sanitization: No sanitization of the content read from external source files is mentioned.
- [SAFE]: The skill uses a tool named
mcp__heroui-react__get_theme_variablesto retrieve configuration data. This is used strictly for design token mapping and is consistent with the skill's purpose. - [SAFE]: No evidence of obfuscation, hardcoded credentials, unauthorized network communication, or persistence mechanisms was found across the skill files.
Audit Metadata