find-edgecase-slop
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git rev-parse --show-toplevelto programmatically identify the repository root directory prior to scanning. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests and processes source code from the local repository, though its actions are limited to non-destructive planning.
- Ingestion points: Reads files and search output from the current working directory git repository.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore prompt-like content found within the scanned files.
- Capability inventory: The skill can execute git commands, modify the agent's operation mode (SwitchMode), and write to the todo list (TodoWrite).
- Sanitization: No validation or sanitization is performed on the file content before it is incorporated into the agent's context.
Audit Metadata