feature-spec

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection because it is designed to ingest and process data from external files (vision and requirements documents) that may be controlled by third parties.
  • Ingestion points: The skill explicitly reads from vision.md, requirements.md, and examines the codebase in backend/ and frontend/ directories.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions that might be embedded within the project's vision or requirement documents.
  • Capability inventory: The skill is primarily focused on document generation and has restricted capabilities; it lacks network access or the ability to execute arbitrary commands, as indicated by the disable-model-invocation: true setting in its metadata.
  • Sanitization: No sanitization or validation logic is applied to the ingested content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 01:42 PM
Security Audit — agent-trust-hub — feature-spec