skills/tstelzer/skills/planning/Gen Agent Trust Hub

planning

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted task requirements and converts them into detailed implementation plans containing code changes.
  • Ingestion points: The skill processes external specifications or requirements provided by the user or from external data sources.
  • Boundary markers: There are no explicit markers or instructions to isolate the input data from the skill's operational logic.
  • Capability inventory: The skill is authorized to write markdown files to the local file system (e.g., <repository-root>/plans/).
  • Sanitization: No sanitization or validation of the input requirements is described, allowing malicious instructions in the input to potentially influence the generated code tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:59 AM