skills/borkweb/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands (mktemp, mv, and echo) to create a temporary file path with a .md extension. This is a standard utility for generating session-specific temporary files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments to tailor the handoff document, creating a surface where malicious input could influence the content generated for subsequent agents. 1. Ingestion points: User arguments provided via argument-hint are interpolated into the prompt. 2. Boundary markers: The instructions do not specify any delimiters or warnings to isolate the user's input from the core prompt. 3. Capability inventory: The skill possesses file system write capabilities and shell command execution (mktemp, mv). 4. Sanitization: No evidence of input validation or escaping for the user-provided arguments is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 08:35 AM