skills/kriscard/skills/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill specifies the use of the GitHub CLI (gh) and the Model Context Protocol (MCP) for accessing public documentation.
  • [SAFE]: There is no evidence of obfuscation, unauthorized data access, or malicious persistence.
  • [PROMPT_INJECTION]: The skill interacts with external content, creating an indirect prompt injection surface. (1) Ingestion points: Technical documentation fetched via WebFetch and GitHub CLI. (2) Boundary markers: Not specified in the instructions. (3) Capability inventory: The skill uses gh CLI in SKILL.md for read-only repository access; it does not have write access to the filesystem or network exfiltration capabilities. (4) Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 07:44 PM
Security Audit — agent-trust-hub — research