build-feature

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data from plan files and GitHub PR comments to drive its workflow, creating an attack surface where malicious input could override intended behavior.
  • [COMMAND_EXECUTION]: Executes repository-specific build and test commands (e.g., 'make build', 'make test') which could run arbitrary code if the repository content is malicious.
  • [DATA_EXPOSURE]: Includes positive security instructions explicitly forbidding the opening of credential files, reducing the risk of secret exposure during the development process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:15 AM
Security Audit — agent-trust-hub — build-feature