skills/sadiksaifi/skills/snap-handoff/Gen Agent Trust Hub

snap-handoff

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to summarize the current conversation context for a future session or different agent. This creates an indirect injection surface where malicious instructions present in the conversation history (e.g., from previously processed untrusted data) could be included in the handoff document and influence the next agent.
  • Ingestion points: Current conversation context in SKILL.md.
  • Capability inventory: File writing via shell commands and reporting the file path in SKILL.md.
  • Boundary markers: Absent; the instructions do not specify how to delimit or sanitize the summarized content.
  • Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill includes a shell command template (HANDOFF_FILE="$(mktemp -t snap-handoff).md"; : > "$HANDOFF_FILE") to create a temporary file. While this is a standard local operation for session management, it demonstrates the use of shell utilities to manage file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:53 AM