golang-pkg-go-dev

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party tool from an external repository using go install github.com/samber/godig/cmd/godig@latest and also references a hosted MCP server at https://godig.samber.dev/mcp.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display documentation, synopses, and README files for any public Go package from pkg.go.dev, which are untrusted external sources that could contain malicious instructions.
  • Ingestion points: Documentation and package data retrieved via the godig CLI/MCP server as described in SKILL.md.
  • Boundary markers: The skill recommends using the -o md flag for chat rendering but does not provide specific instructions or delimiters to isolate the agent from potentially adversarial instructions embedded in the external documentation.
  • Capability inventory: The skill environment permits the use of powerful tools including Bash, Write, and Edit, creating a potential impact if the agent follows instructions found in external package docs.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from pkg.go.dev before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:09 AM
Security Audit — agent-trust-hub — golang-pkg-go-dev