skills/beeltec/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill aggregates conversation context, workspace state, and file diffs into a markdown file for future use.
  • Ingestion points: Step 2 in SKILL.md identifies conversation history, branch state, and diffs as sources.
  • Boundary markers: None are specified for the handoff file content to distinguish between context and instructions.
  • Capability inventory: Step 4 in SKILL.md performs file system writes to create the handoff document.
  • Sanitization: Step 6 in SKILL.md includes filtering for secrets and environment dumps, but does not explicitly sanitize for embedded instructions that might influence the next agent.
  • [COMMAND_EXECUTION]: The skill utilizes standard system commands (git rev-parse, git status) to determine the repository root and state. These operations are limited to local context gathering and are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 03:00 PM
Security Audit — agent-trust-hub — handoff