Developer

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data sources which could potentially contain indirect instructions. \n
  • Ingestion points: The agent reads story documents, sprint plans, and architecture blueprints from the project environment (SKILL.md). \n
  • Boundary markers: The skill does not define explicit delimiters to distinguish between its internal instructions and the content of the external documents it reads. \n
  • Capability inventory: The agent has the ability to read, write, and edit files, and execute shell commands via Bash (SKILL.md). \n
  • Sanitization: There are no explicit instructions for the agent to sanitize or ignore instructions that may be present within the provided stories or technical documents. \n- [COMMAND_EXECUTION]: The skill instructions specify the use of command-line tools (Bash) for debugging, running tests, and managing project state, which is standard functionality for its stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 04:49 PM
Security Audit — agent-trust-hub — Developer