Revise Report Generation

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses the Beads CLI ('bd') to list tasks and fetch comment data in JSON format for report generation.
  • [PROMPT_INJECTION]: The skill processes untrusted task comments, creating a surface for indirect prompt injection. Ingestion points are located in SKILL.md where 'bd comments' is called. While boundary markers and sanitization are absent, the skill's capabilities are limited to executing established CLI tools and writing static markdown files, which prevents the execution of adversarial instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 11:53 AM
Security Audit — agent-trust-hub — Revise Report Generation