agentsmd-optimize

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands like ls and wc -l to perform repository discovery and verify documentation claims against the actual file system state.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes user-provided documentation files.
  • Ingestion points: The skill reads contents from CLAUDE.md, AGENTS.md, and other repository files identified during discovery.
  • Boundary markers: The skill recognizes and protects auto-generated content marked by <!-- vibeguard-start --> and <!-- vibeguard-end --> tags.
  • Capability inventory: The skill possesses file-read and file-write capabilities, along with shell execution for discovery commands (ls, wc).
  • Sanitization: The skill explicitly instructs the agent to audit for instruction-override or concealment markers (referenced as SEC-13) and mandates user confirmation for all edits to high-context or global files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 02:13 PM
Security Audit — agent-trust-hub — agentsmd-optimize