skills/otrebu/skills/tmp-snapshot/Gen Agent Trust Hub

tmp-snapshot

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to manage conversation snapshots by writing to the /tmp directory. No evidence of data exfiltration, network operations, or unauthorized credential access was found.
  • [SAFE]: The instruction set is transparent and focuses on formatting and organizing chat data. It does not attempt to bypass safety filters or obfuscate its logic.
  • [SAFE]: Indirect Prompt Injection Surface: The skill processes conversation data, which is inherently untrusted.
  • Ingestion points: User-provided conversation history (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: Local file system write access (SKILL.md)
  • Sanitization: Content is processed for summarization or extraction without specific character filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:56 AM
Security Audit — agent-trust-hub — tmp-snapshot