code-tidy
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading the contents of Java files to identify where to add or update Javadoc comments. Maliciously crafted comments within the processed source code could attempt to influence the agent's behavior.
- Ingestion points: The agent reads Java file content as part of the tidying workflow described in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded instructions within the source files.
- Capability inventory: The skill allows the agent to modify local source code files based on the content it reads.
- Sanitization: No specific sanitization or filtering of the file content is performed before processing.
Audit Metadata