build-feature

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via external data sources.
  • Ingestion points: The agent fetches and parses data from GitHub issue bodies (gh issue view), GitHub project items (gh project item-list), and local decision records (docs/decisions/) to define the implementation plan.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded natural language instructions within the fetched external data.
  • Capability inventory: The skill possesses significant capabilities, including executing shell commands (git, gh, pnpm), modifying project files across the entire stack, and running local test suites which could be exploited if malicious instructions are present in the ingested plan.
  • Sanitization: The skill does not implement validation or sanitization of the fetched issue content before using it to drive code generation and execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 09:14 PM