autodev
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands defined by the user or auto-detected from project files such as package.json, pyproject.toml, or Makefile via the Bash tool to verify code changes and perform initialization.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by ingesting instructions from an external file (PRD).
- Ingestion points: The file path provided for the prd parameter in Phase 0 and read during Phase 2.
- Boundary markers: No delimiters or warnings are used to isolate the PRD content from the agent's core instructions.
- Capability inventory: The skill uses Write, Edit, and Bash tools to implement code changes based on the PRD content.
- Sanitization: No sanitization or validation is performed on the ingested text before implementation.
Audit Metadata