deepchat-sdd

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill performs analysis of existing source code and documentation to inform the creation of new design documents, which exposes the agent to instructions potentially embedded in the project data.
  • Ingestion points: The workflow in SKILL.md requires the agent to 'Inspect the current code and docs first.'
  • Boundary markers: No specific delimiters or safety instructions are defined to isolate the ingested project data from the agent's core instructions.
  • Capability inventory: The skill can create folders and files, execute shell commands through pnpm, and interact with the GitHub CLI (gh).
  • Sanitization: The skill lacks explicit sanitization or validation logic for the content read from the project environment before it is used in documentation or plans.
  • [COMMAND_EXECUTION]: The workflow requires running project-specific maintenance scripts using pnpm (format, i18n, lint, typecheck). These commands execute logic provided by the repository's own configuration.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) for issue synchronization. It explicitly mandates developer approval before performing these operations, which serves as a control for automated external interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 11:21 AM
Security Audit — agent-trust-hub — deepchat-sdd