resume-handoff
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The instructions direct the agent to 'Run the handoff's re-grounding commands to confirm the verified state still holds'. This creates a path for executing arbitrary shell commands provided in an external document, which could be malicious if the document source is untrusted.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes data from external handoff documents and acts upon them. 1. Ingestion points: Handoff document file path. 2. Boundary markers: Absent. 3. Capability inventory: Execution of git, gh, grep, and arbitrary 're-grounding' commands. 4. Sanitization: Absent. No verification of command safety or content integrity is performed before execution.
- [NO_CODE]: This skill contains no executable scripts or binary files, consisting entirely of markdown instructions.
Audit Metadata