skills/steveclarke/dotfiles/simplify/Gen Agent Trust Hub

simplify

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using git and gh (GitHub CLI) to identify branches, find merge bases, and extract diffs for analysis.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface (Category 8).\n
  • Ingestion points: Untrusted data enters the agent context through git diff output, which may contain attacker-controlled code or comments (SKILL.md).\n
  • Boundary markers: There are no explicit delimiters or instructions for the agent to ignore embedded commands within the diff content.\n
  • Capability inventory: The skill instructions empower the agent to "Fix issues directly," which involves modifying the project's source code.\n
  • Sanitization: No validation or sanitization mechanisms are present to filter out potentially malicious instructions embedded in the code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:40 PM
Security Audit — agent-trust-hub — simplify