review-hog-authoring

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow for ingesting user requirements to generate custom automated review logic.
  • Ingestion points: User input is collected during the interview step (Step 2) to define the specific focus of the new review lens.
  • Boundary markers: The skill relies on the agent to interpret user needs and translate them into a structured markdown body following provided templates.
  • Capability inventory: The skill uses vendor-provided tools including posthog:skill-create and posthog:skill-update to persist configurations.
  • Sanitization: Logic drafting is guided by structural requirements (lane, hunting grounds, finding bar) defined in the skill text.
  • [DYNAMIC_EXECUTION]: The skill enables the generation of new agent instruction sets as part of its primary purpose.
  • Skill Generation: It utilizes standard platform capabilities to install new logic rows based on dynamic user requirements.
  • Primary Purpose: These capabilities are the central function of the skill for extending the automated reviewer's specialist capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:40 AM
Security Audit — agent-trust-hub — review-hog-authoring