to-spec

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted conversation context and codebase data to generate a specification that is published to an external issue tracker. This creates a surface for indirect prompt injection where adversarial input in the conversation could be persisted into project documentation.
  • Ingestion points: Conversation context and codebase exploration (SKILL.md).
  • Boundary markers: Not specified in instructions.
  • Capability inventory: Repository exploration and publishing to an external issue tracker (SKILL.md).
  • Sanitization: No explicit instructions for sanitizing or validating ingested data.
  • [EXTERNAL_DOWNLOADS]: The instructions refer to a setup command /setup-matt-pocock-skills which is required for the skill to function correctly (SKILL.md). This indicates a dependency on external configuration or tooling that may involve downloading or executing external scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:08 AM
Security Audit — agent-trust-hub — to-spec