tracker-creator

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external documents (PRDs and Playbooks). While the instructions do not explicitly include boundary markers to separate data from instructions or specific sanitization steps, the skill's capabilities are limited to generating and writing a static markdown file, representing a minimal attack surface.
  • Ingestion points: Reads content from project PRD and Execution Playbook files.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Writes a markdown file to the local directory (e.g., docs/TRACKER.md) or creates an artifact.
  • Sanitization: No explicit sanitization or filtering of input content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 05:55 AM
Security Audit — agent-trust-hub — tracker-creator