anfra-read-logs
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
anfra logscommand-line utility to retrieve log data for debugging purposes. This involves standard shell execution of a vendor-provided tool with various flags like--since,--yaml, and--jqfor filtering. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze log entries, which are external data sources that could potentially contain maliciously crafted content meant to influence agent behavior.
- Ingestion points: Data enters the agent's context through the output of the
anfra logscommand, as described inSKILL.md. - Boundary markers: The instructions do not specify any delimiters or safety markers to help the agent distinguish between log data and instructions.
- Capability inventory: While the skill enables reading logs via command execution, it does not include capabilities for file system modification or outbound network requests within the provided file.
- Sanitization: There are no instructions for the agent to sanitize or filter the log content before analysis.
Audit Metadata