pm-release-plan

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and templates focus on professional product management tasks. No evidence of malicious behavior, credential theft, or unauthorized network access was found.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process data from external requirements documents (MRDs/PRDs). * Ingestion points: MRD/PRD documents (referenced in SKILL.md) * Boundary markers: Absent * Capability inventory: Access to Bash, Write, Edit, and Read tools (SKILL.md) * Sanitization: No explicit content validation or sanitization of external documents is specified
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 05:16 PM
Security Audit — agent-trust-hub — pm-release-plan