skills/benjaming/ai-skills/done/Gen Agent Trust Hub

done

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an indirect injection surface (Category 8) because it processes untrusted data from external sources (Jira/JSON files).
  • Ingestion points: ~/.claude/daily-tasks/$(date +%Y-%m-%d).json (specifically task summaries and Jira keys).
  • Boundary markers: Absent. The skill interpolates JSON values directly into the output summary.
  • Capability inventory: Execution of cat and date via bash; file writing via a 'Write tool'.
  • Sanitization: Absent. There is no evidence of escaping or filtering of the strings read from the JSON file before they are displayed to the user or processed.
  • Data Exposure & Exfiltration (SAFE): The skill accesses ~/.claude/daily-tasks/. While this involves reading from the user's home directory, the access is limited to a specific application folder necessary for the skill's stated purpose.
  • Command Execution (SAFE): Uses standard system utilities (cat, date) to perform routine file and time operations. No arbitrary command execution or pipe-to-bash patterns found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:02 AM