product-vision-steering

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its reliance on untrusted external data from the project repository.
  • Ingestion points: The workflow instructs the agent to read manifest files such as package.json, pyproject.toml, and requirements.txt, as well as scanning the codebase directory structure and existing documentation.
  • Boundary markers: There are no defined boundary markers or instructions for the agent to ignore potentially malicious content or instructions embedded within the analyzed codebase files.
  • Capability inventory: The skill possesses the capability to write files to the local directory documentation/steering/ and publish content to external Confluence pages using Atlassian MCP tools.
  • Sanitization: The instructions do not specify any sanitization, validation, or escaping of the ingested data before it is processed into the steering document templates and published.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 12:41 PM