show-me-your-work

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash script scripts/log.sh that performs basic file operations (mkdir, printf) and uses date to generate timestamps. These are standard operations for the skill's logging purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and log descriptions of decisions ('why', 'decision', 'result'). If these fields are populated from untrusted external data without sanitization, it creates a surface for indirect prompt injection, although the current implementation uses a helper script that performs basic character cleaning.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 02:21 PM
Security Audit — agent-trust-hub — show-me-your-work