skills/udecode/better-convex/dig/Gen Agent Trust Hub

dig

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones source code from GitHub repositories to retrieve documentation. This utilizes a well-known service for its intended functionality.
  • [COMMAND_EXECUTION]: The skill executes shell commands including git clone, mkdir, and ls to manage repositories in the /tmp/cc-repos directory.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it analyzes untrusted data from external repositories.
  • Ingestion points: Files such as READMEs and source code within cloned repositories at /tmp/cc-repos/{repo-name}.
  • Boundary markers: There are no specified delimiters or instructions to ignore potential commands within the ingested files.
  • Capability inventory: The agent uses a research sub-agent with file system access to explore the downloaded content.
  • Sanitization: No sanitization or validation is applied to the repository content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:20 AM