backlog-curator

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/analyze_backlog.py to calculate task priorities. This is a standard and expected operation for the skill's purpose.
  • [PROMPT_INJECTION]: The skill processes data from .pm/backlog/items.yaml, which represents an indirect prompt injection surface if the backlog contains untrusted input. However, this is inherent to any task management functionality.
  • Ingestion points: .pm/backlog/items.yaml (reading item titles and descriptions).
  • Boundary markers: Absent; the skill does not define specific delimiters for separating data from instructions.
  • Capability inventory: Local file system access (read/write) and execution of the scripts/analyze_backlog.py subprocess.
  • Sanitization: Absent; the skill relies on the structured format of the YAML file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 10:50 AM