validator-status
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
agent-validate statususing theBashtool to retrieve summary information about recent validator sessions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files (.debug.log, check_.log, review_.json) which may contain snippets from code being validated.
- Ingestion points: Log files and JSON violation reports listed in the status output.
- Boundary markers: Absent; the skill does not specify the use of delimiters when reading log content.
- Capability inventory: The skill uses Bash to run commands and the Read capability to access local files.
- Sanitization: Absent; the agent processes and summarizes raw log content directly.
Audit Metadata