ss-reverse-spec

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill analyzes untrusted project data including source code, documentation, and database schemas.
  • Ingestion points: Project source code, README files, API definitions, and database migrations (SKILL.md).
  • Boundary markers: Absent; the instructions lack explicit delimiters or instructions to ignore instructions embedded in processed data.
  • Capability inventory: The skill reads local project files and writes documentation to the local filesystem.
  • Sanitization: Absent; no explicit content sanitization or validation is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 09:08 AM
Security Audit — agent-trust-hub — ss-reverse-spec