skills/letta-ai/skills/morph-warpgrep/Gen Agent Trust Hub

morph-warpgrep

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading the @morphllm/morphsdk and @morphllm/morphmcp packages via NPM/npx. It also involves installing the ripgrep utility through system package managers (brew or apt) and cloning a test repository from the author's GitHub (github.com/letta-ai/letta-code). These resources are documented as prerequisites for the tool's operation.
  • [COMMAND_EXECUTION]: The instructions include shell commands for installing dependencies and running a local test script (scripts/test-warpgrep.ts) using the bun runtime to verify search results on a specified repository path.
  • [DATA_EXFILTRATION]: To provide agentic code search, the WarpGrep tool transmits search queries and local code fragments to the Morph API (api.morphllm.com) for refinement. This behavior is the intended core functionality of the cloud-assisted search service.
  • [PROMPT_INJECTION]: The skill processes untrusted data from local repositories, which constitutes a surface for indirect prompt injection.
  • Ingestion points: Local codebase files read during the WarpGrep search process in scripts/test-warpgrep.ts and mentioned in SKILL.md.
  • Boundary markers: The skill does not explicitly mention delimiters or instructions to ignore embedded prompts within the files being searched.
  • Capability inventory: The skill performs file reading and directory listing using local tools like ripgrep and the Morph SDK.
  • Sanitization: The provided documentation and test script do not contain explicit sanitization or filtering of the content read from files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:38 AM