check-logs
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it reads and processes terminal output from external applications that may contain malicious instructions.
- Ingestion points: Terminal buffer content read via
herdr pane read(SKILL.md). - Boundary markers: Absent. No specific delimiters are used to wrap the ingested log data.
- Capability inventory: The skill can interact with terminal panes via
herdr pane send-keysandherdr pane send-text(SKILL.md). - Sanitization: No sanitization or filtering of captured log output is performed.
- [COMMAND_EXECUTION]: The skill utilizes
herdr pane send-textandherdr pane send-keysto interact with other terminal panes. If the agent misidentifies a standard shell pane as a Turborepo TUI, it could inadvertently execute arbitrary commands.
Audit Metadata