api-contract

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a collection of markdown templates and process guidelines for API documentation and does not include any executable code, network operations, or sensitive file access.
  • [PROMPT_INJECTION]: The skill includes instructions that create an indirect prompt injection vulnerability surface through file processing.
  • Ingestion points: Untrusted data is ingested from .claude/sprint/[N]/specs.md to define the feature scope and requirements.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when reading external specifications.
  • Capability inventory: The skill's primary capabilities involve reading and writing markdown files within the localized project sprint directory.
  • Sanitization: Absent; the content from the specifications is processed and interpolated into the generated API contract without explicit validation or sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 01:17 AM
Security Audit — agent-trust-hub — api-contract