middle
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted source code and configuration files. Malicious instructions hidden within these files (such as in comments or documentation) could attempt to influence the agent's behavior during analysis or the automated 'tidy' operation.
- Ingestion points: The skill reads all files within the project scope provided by the user (
SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded prompts within the source content.
- Capability inventory: The skill has read access to the project directory, write access to modify code (with user approval for larger tasks or autonomously for single small files), and can execute development validation commands like
npm testorbuild(SKILL.md). - Sanitization: No sanitization is performed on the ingested code or comments before processing.
Audit Metadata