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

spec

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill behaves as a standard documentation generator.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it analyzes external repository content to generate specifications.
  • Ingestion points: Read operations on README.md, package.json, FORMAT.md, and project source code during the DISTILL and BACKPROP routines.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the analyzed code.
  • Capability inventory: File-write access is limited to the SPEC.md file.
  • Sanitization: Absent; content is extracted directly from source files.
  • Risk Mitigation: The threat is minimal because the skill only writes to a documentation file and mandates human-in-the-loop approval with a diff display before any changes are committed.- [NO_CODE]: The skill consists entirely of natural language instructions and logic for the AI agent; it does not include or execute any companion scripts or binaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:09 PM