skills/raddue/crucible/spec/Gen Agent Trust Hub

spec

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it ingests untrusted GitHub issue content. This risk is managed through isolated sub-agent dispatches and a specific security scan phase. * Ingestion points: Fetches title and body content from GitHub epics and tickets. * Boundary markers: Employs template placeholders to encapsulate untrusted issue data. * Capability inventory: Capable of modifying codebase documentation via git and creating local state files. * Sanitization: Implements a keyword-based Security Signal Scan (Step 3.5) to detect sensitive categories like credentials and PII.
  • [COMMAND_EXECUTION]: Uses git and gh CLI tools for repository management, which is consistent with the skill's intended purpose of managing technical documentation within GitHub-hosted projects.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 09:50 PM