skills/juliusbrussee/cavekit/spec/Gen Agent Trust Hub

spec

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill functions as a documentation manager, reading local project files to maintain a specification document. It does not perform network operations, access sensitive credentials, or execute arbitrary code.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from repository files to generate documentation. 1. Ingestion points: Reads FORMAT.md, SPEC.md, and project files (README, package.json, source code). 2. Boundary markers: None explicitly mentioned to separate repository content from agent instructions. 3. Capability inventory: Capabilities are limited to writing Markdown content to SPEC.md; sub-agent spawning and automated builds are explicitly listed as non-goals. 4. Sanitization: No explicit sanitization or filtering of processed content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:19 PM
Security Audit — agent-trust-hub — spec