skills/rheinmir/skills/orca-handover/Gen Agent Trust Hub

orca-handover

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard version control commands (git log, git status) and local repository maintenance scripts (fdk/tools/medic.py) to gather evidence for the handover file. These operations are read-only and strictly limited to the repository scope.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes repository metadata to generate its summaries. \n
  • Ingestion points: git log, git status, and medic.py output (SKILL.md).\n
  • Boundary markers: Absent.\n
  • Capability inventory: File writing to llmwiki/ and local python3 execution (SKILL.md).\n
  • Sanitization: Absent.\n This constitutes an ingestion of external data for documentation purposes, posing minimal risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 02:25 AM