03-api-specification

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection because it processes untrusted external data (SRS and HLD documents) and uses that data to generate implementation-ready contracts.
  • Ingestion points: SRS_Draft.md, HLD.md, and tech_stack.md are read from the local file system as primary context.
  • Boundary markers: Absent. The instructions do not employ specific delimiters or "ignore previous instructions" warnings when interpolating the content of context files into the prompt logic.
  • Capability inventory: The skill possesses the ability to read arbitrary project files and write the resulting API_Specification.md and openapi.yaml files.
  • Sanitization: There is no evidence of filtering or validation for instructions embedded within the functional requirements documents, allowing potentially malicious text in the SRS to influence the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:45 PM
Security Audit — agent-trust-hub — 03-api-specification