generate-interface-uml
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes local source code, which creates a potential surface for instructions embedded in code comments to influence the agent's behavior.
- Ingestion points: Step 2 involves analyzing .h and .cpp files for interface definitions.
- Boundary markers: There are no specific delimiters defined to separate the code content from the agent's instructions.
- Capability inventory: The skill performs file system searches using grep and writes .puml files to the user's directory.
- Sanitization: The skill does not explicitly sanitize or validate the content retrieved from the codebase.
- [COMMAND_EXECUTION]: The skill uses the grep command-line tool to recursively search for interface implementation details within the repository.
Audit Metadata