skills/dmmulroy/.dotfiles/to-prd/Gen Agent Trust Hub

to-prd

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from the conversation history and repository files to generate the PRD content. However, this behavior is central to the skill's primary function and no malicious intent was found.
  • Ingestion points: Processes conversation context and performs repository exploration to gather information.
  • Boundary markers: No explicit delimiters are used to separate ingested content from the PRD template instructions.
  • Capability inventory: The skill utilizes repository exploration (file reads) and tool calls to publish to the issue tracker.
  • Sanitization: The skill does not implement specific sanitization or escaping for the synthesized content before publishing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 01:34 PM
Security Audit — agent-trust-hub — to-prd