scout
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands, specifically
gitandsed, to identify which files have changed in a repository. This is the intended functionality for a code analysis tool and utilizes standard CLI utilities. - [INDIRECT_PROMPT_INJECTION]: The skill reads the entire content of files detected via git or specified by the user to perform its analysis. This creates a vulnerability surface where instructions hidden in code or comments could potentially influence the agent's behavior.
- Ingestion points: The full content of any file touched by a diff is read into the agent's context as instructed in
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions found within the code being analyzed.
- Capability inventory: The skill possesses file read capabilities and the ability to execute
gitCLI commands, but lacks network or file-write permissions. - Sanitization: The skill does not implement any filtering or escaping of the file content before it is processed by the model.
Audit Metadata