searching-history
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the
glhfutility, which is a command-line tool for searching and managing conversation history, sessions, and project data. - [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection because it retrieves and processes content from previous conversation logs.
- Ingestion points: Content is ingested into the agent context via the output of
glhf searchandglhf sessioncommands as specified inSKILL.md. - Boundary markers: The instructions do not provide delimiters or specific guidelines for the agent to treat historical content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill has access to the
Bashtool, which allows for broad system interaction and command execution. - Sanitization: The skill does not mention or implement any sanitization, filtering, or validation of the historical data before it is returned to the agent context.
Audit Metadata